Content Sanitization of Ingested Artifacts

An event-triggered AI agent is a synthetic subject whose runs are started by a system event rather than a direct conversational request. This may include a frontend action, webhook, queue item, form submission, file drop, inbound email, application event, or record arriving in a data pipeline.

This deployment pattern creates an elevated exposure condition because the person or system that triggers the run may be different from the person who controls the input. The agent may run with a standing application identity and access to customer records, ticket queues, internal documents, communications, or pipeline data, while the event content may originate from an external or low-trust source.

The primary risk is event-driven indirect prompt injection. Form fields, payloads, queued rows, uploaded files, or inbound messages may contain instructions that the agent treats as task context. A malicious instruction can therefore be planted by a malicious individual and executed later when the workflow processes the item.

A related risk is unattended repetition. Event-triggered agents often process backlogs, queues, or recurring inputs without a human reviewing each run. A poisoned input or flawed directive may produce harmful outputs at machine speed while appearing to be normal workflow throughput.

Investigators should review the agent’s directive, trigger conditions, event payloads, queue records, service identity, workflow permissions, input sources, run history, tool calls, output destinations, and downstream actions. Particular attention should be given to externally controlled fields, repeated adverse outcomes across similar records, and logs that fail to show which input content caused the agent’s action.

Investigative Relevance

Event-triggered AI agents are relevant because they decouple human oversight from agent execution. The run may be authorized by the workflow, while the effective instruction is supplied through data controlled by an external party, customer, vendor, compromised account, or low-trust source.

This section is especially relevant where agents process public forms, inbound webhooks, emails, file uploads, watched folders, customer relationship management records, ticket queues, data pipelines, or application events without human review before action.

Enterprise retrieval access is the configuration of corpora, indexes, connectors, and Retrieval-Augmented Generation (RAG) pipelines that a synthetic subject can retrieve from. A corpus is a collection of documents, records, messages, files, or other source material made available for search or retrieval. RAG is a design pattern where relevant source material is retrieved before the synthetic subject generates an answer or takes action.

This configuration creates an elevated exposure condition because retrieval defines what internal information can enter the synthetic subject’s context. If retrieval spans mailboxes, documents, tickets, customer records, wikis, source code, or other enterprise stores, the synthetic subject may combine information across repositories, sensitivity levels, and access boundaries.

The primary risk is retrieval beyond entitlement. A synthetic subject may retrieve, summarize, or expose information that the human requester is not authorized to view. This may occur through shared indexes, broad connectors, cached embeddings, service identities, incomplete query-time access checks, or retrieval pipelines that do not enforce per-user permissions.

A related risk is untrusted content in retrieval context. Externally sourced documents, inbound emails, customer records, support tickets, uploaded files, or partner content may be indexed and later retrieved into the synthetic subject’s context. If that content contains malicious or misleading instructions, it may influence the synthetic subject during an otherwise legitimate request.

Investigators should review retrieval configuration, connected corpora, index membership, connector permissions, query logs, documents returned, requester identity, access-control decisions, prompt and response records, and output destinations. Particular attention should be given to cross-boundary retrieval, sensitive content in outputs, externally sourced documents, and cases where retrieved material exceeded the requester’s entitlement.

Investigative Relevance

Enterprise retrieval access is relevant because retrieval configuration determines what information a synthetic subject can see and use. Weak retrieval boundaries may turn an assistant or agent into a bridge between restricted information and an unauthorized requester.

This section is especially relevant where synthetic subjects retrieve from enterprise search indexes, RAG pipelines, mailboxes, file stores, collaboration platforms, ticketing systems, customer relationship management platforms, source repositories, or shared document corpora.

Indirect untrusted-content invocation occurs when attacker-controlled or low-trust content causes a synthetic subject to act. The effective instruction is embedded in data the synthetic subject retrieves, ingests, summarizes, renders, or processes, rather than being issued directly by the apparent operator.

This may include instructions hidden in email, webpages, documents, customer relationship management fields, support tickets, pull request comments, uploaded files, calendar invites, chat messages, tool outputs, or other content sources. The synthetic subject may treat the embedded instruction as part of the task context and execute it as if it were a legitimate command.

This invocation creates an elevated exposure condition because the person who triggers the synthetic subject may not be the person who supplied the effective instruction. An employee may ask an assistant to summarize a mailbox, review a document, process a lead, or inspect a pull request, while the actual behavioral instruction comes from external or attacker-controlled content previously placed in that source.

The primary risk is indirect prompt injection. A malicious instruction may cause the synthetic subject to retrieve private data, override constraints, call tools, generate outbound links, render images, transmit information, or combine internal data with an external communication path. This is especially significant where the same context contains private data, untrusted content, and outbound connectivity.

Investigators should review the ingested content, retrieval records, tool outputs, prompt and response logs, rendered links and images, external fetches, web proxy records, Data Loss Prevention (DLP) alerts, requester identity, and downstream tool calls. Particular attention should be given to instruction-like text in retrieved content, invisible or obfuscated payloads, auto-rendered markdown images, new or recently registered domains, character-by-character request patterns, and outputs that combine private data with an outbound channel.

Investigative Relevance

Indirect untrusted-content invocation is relevant because the apparent user request may be benign while the effective command is supplied by another party. The investigation must reconstruct not only who invoked the synthetic subject, but which retrieved or ingested content shaped the action.

Model Context Protocol (MCP) invocation occurs when a synthetic subject is caused to act, change behavior, select tools, or continue a workflow through MCP-supplied content. MCP is an integration pattern that allows a synthetic subject to discover and use external tools, data sources, and actions through a structured interface.

This invocation creates an elevated exposure condition because MCP servers can supply model-visible information before, during, and after tool use. Tool descriptions, server instructions, schemas, tool outputs, resource content, sampling requests, prompts, and connector metadata may all enter the synthetic subject’s context and influence its behavior.

The primary risk is protocol-mediated instruction flow. The synthetic subject may treat MCP-supplied text as trusted operational context even when it originates from a third-party server, compromised connector, unapproved tool, or attacker-influenced resource. This may cause the synthetic subject to call tools, disclose information, change reasoning, prefer malicious servers, or pass sensitive context across boundaries.

Investigators should review MCP server inventory, tool definitions, server instructions, schemas, tool-list responses, resource reads, sampling requests, prompt templates, tool outputs, connection history, version changes, and tool-call logs. Particular attention should be given to instruction-bearing metadata, changed tool descriptions, untrusted server output, cross-server influence, and behavior that begins when an MCP server connects or returns content.

Investigative Relevance

MCP invocation is relevant because MCP can introduce instructions into a synthetic subject through several protocol surfaces, not only through executed tool calls. A synthetic subject may be influenced when a server connects, when tools are listed, when resources are read, when prompts are supplied, or when tool output is returned.

This section is especially relevant where synthetic subjects connect to MCP servers, tool registries, marketplace connectors, local developer tools, SaaS integrations, filesystem tools, browser tools, or third-party agent tool platforms.

Source provenance obfuscation occurs when a synthetic subject’s output hides, omits, or misrepresents the true source of the data, instruction, or context that influenced its behavior. The visible output may cite an innocuous source, trusted record, private channel, or retrieved document while omitting the upstream content that actually caused the response or action.

This opacity condition frustrates investigation because the cited source may not be the causal source. A synthetic subject may produce an answer that appears grounded in approved material, while the operative instruction came from hidden text, an attacker-controlled message, a tool result, a retrieved comment, or another upstream source not shown to the user.

The primary risk is false source confidence. Investigators, users, or reviewers may inspect the visible citation and conclude that the response was properly grounded, while the actual source of influence remains outside the cited evidence chain. This can delay containment, misdirect review, and cause investigators to inspect the wrong document, channel, record, or tool output.

A related risk is missing upstream provenance. Retrieved or summarized content may be copied through multiple layers before reaching the synthetic subject. As content passes through summaries, citations, tool outputs, shared context, or generated records, the original source may become hidden or detached from the final answer.

Investigators should review cited sources, retrieved records, raw source content, upstream messages, hidden comments, tool outputs, prompt and response logs, provenance tags, source ranking, and generated citations. Particular attention should be given to citations that do not contain the asserted content, outputs shaped by uncited material, invisible markdown comments, zero-width Unicode, hidden instructions, and answers whose visible source trail begins after the true originating source.

Investigative Relevance

Source provenance obfuscation is relevant because a synthetic subject’s visible citation or grounding trail may not identify the content that caused its behavior. The investigator must reconstruct the full source chain, including upstream material that was retrieved, summarized, hidden, or omitted from the final output.

This section is distinct from data exfiltration and indirect prompt injection. The data leak belongs to Adverse Outcome, and the injected instruction belongs to Invocation. This Opacity section concerns the concealment or loss of source provenance that frustrates reconstruction.

This section is especially relevant where synthetic subjects generate citations, summarize retrieved content, process hidden comments, use Retrieval-Augmented Generation (RAG), consume tool outputs, or operate in collaboration platforms where content from one channel, record, or document can influence output attributed to another.

A public Q&A knowledge bot is a synthetic subject directed to answer open questions from a defined document set, knowledge base, website corpus, policy library, or other indexed source material. This may include public-sector guidance bots, legal information assistants, regulatory tools, policy question-and-answer services, and product documentation assistants.

This directive creates an elevated exposure condition because the synthetic subject may convert source material into authoritative-sounding guidance, even when the answer is incomplete, outdated, overgeneralized, or wrong. Retrieval-Augmented Generation (RAG) can improve grounding by retrieving source passages before generation, but it does not prevent unsupported conclusions, missed exceptions, or excessive certainty.

The primary adverse outcome is user reliance on incorrect or unlawful guidance. A public Q&A knowledge bot may state that a prohibited action is allowed, that an obligation does not apply, or that a policy permits conduct it does not. This is especially significant where the operator is a government body, regulated entity, legal service, healthcare provider, employer, or other trusted institution.

A secondary risk is exposure or manipulation of the document set. If the synthetic subject retrieves from internal documents, draft policy, sensitive records, or unapproved repositories, it may disclose material not intended for public release. If the indexed corpus can be influenced by external content, user submissions, or weak document governance, the retrieval channel may also become a poisoning path.

Investigators should review the synthetic subject’s directive, retrieval configuration, source corpus, grounding behavior, citation handling, ingestion process, access boundaries, transcript logs, and retrieval controls. Particular attention should be given to unsupported answers, contradictions with authoritative policy, exposure of out-of-scope material, and whether indexed content was current, authorized, and resistant to manipulation.

Investigative Relevance

Public Q&A knowledge bots are relevant because they can transform source documents into operational guidance at scale. The synthetic subject may not be authorized to create policy, interpret law, approve business conduct, or provide regulated advice, but users may treat its output as if it does.

An internal knowledge assistant is an employee-facing artificial intelligence system that answers questions using internal documents, wikis, file stores, tickets, policies, procedures, and other indexed sources. It is commonly implemented using Retrieval-Augmented Generation (RAG), where relevant source material is retrieved before an answer is generated.

This deployment pattern creates an elevated exposure condition because the retrieval index becomes part of the synthetic subject’s instruction surface. Any indexed document, ticket, page, comment, or shared file may later enter the assistant’s context. If that content contains malicious or misleading instructions, the assistant may treat them as relevant during an ordinary employee query.

The primary risk is that a planted or low-trust document can influence answers drawn from higher-trust material. A malicious outsider or low-trust insider may not need direct access to sensitive repositories if they can place content somewhere the assistant indexes.

A related risk is permission and access-boundary failure. The assistant may retrieve, summarize, or infer information from documents the human requestor is not entitled to view. This can occur through a shared service identity, broad retrieval index, cached embeddings, inherited connector permissions, or weak query-time access controls.

Investigators should review the assistant’s directive, retrieval configuration, indexed sources, ingestion process, access controls, source ranking, logs, and retrieved source records. Particular attention should be given to retrieval outside the employee’s entitlement, embedded instructions in indexed material, and answers that are not grounded in approved sources.

Investigative Relevance

Internal knowledge assistants are relevant to the SITM because they convert internal document stores into conversational answers at workforce scale. Their retrieval process may combine content across repositories, trust levels, and access boundaries in ways that employees cannot easily observe.

An in-app text generation feature is an embedded artificial intelligence capability that generates, summarizes, drafts, rewrites, or explains content inside an existing application surface. It may read documents, messages, records, tickets, notes, or other user-accessible content, then render output inline as part of the product workflow.

This deployment pattern creates an elevated exposure condition because the content the feature must ingest to perform its task can also become the manipulation vector. A malicious instruction hidden in a message, uploaded file, record, comment, or document may influence the generated output during an ordinary summarize, draft, or generate action.

The primary risk is that manipulated output appears as trusted application content. If links, images, markdown, or generated text are rendered inline, the feature may mislead the employee, expose sensitive content, or create an outbound path without a distinct synthetic subject identity in the activity trail.

Investigators should review the feature’s directive, input sources, rendering behavior, output logs, external link handling, image loading, markdown support, and provenance records. Particular attention should be given to hidden instructions in ingested content, output that includes external destinations, and whether generated text is distinguishable from user- or application-authored content.

Investigative Relevance

In-app text generation is relevant because it embeds synthetic subject output directly into trusted product workflows. The feature may appear to be a normal application function, while its output is shaped by untrusted content processed during the task.

A user action trigger occurs when an action in an application interface starts an agent run. This may include submitting a form, clicking a button, saving a record, uploading a file, updating a field, or completing another workflow step.

This deployment pattern creates an elevated exposure condition because the action that starts the run may not be the same as the content that shapes it. The agent may process free-text fields, attachments, comments, descriptions, or uploaded records as task context, even where that content was supplied by an external or low-trust submitter.

The primary risk is delayed execution of injected content. A malicious instruction may be planted in a frontend field or submitted record, then executed later when an internal employee opens, reviews, routes, or processes the item. The run may execute under the application, workflow, or employee identity, while the effective instruction came from the external submitter.

Investigators should review the trigger action, submitted fields, attachments, record history, user identity, workflow permissions, agent run logs, tool calls, and downstream actions. Particular attention should be given to free-text fields, externally supplied content, and cases where an internal user triggered processing of a record created or modified by someone else.

Investigative Relevance

User action triggers are relevant because they allow external or low-trust content to influence an agent run through normal application behavior. The employee may appear to have initiated the run, but the instruction path may originate in submitted data.

This sub-section is especially relevant where agents process web forms, customer relationship management records, support tickets, uploaded files, comments, case notes, lead forms, application records, or other frontend-supplied content.

A webhook event trigger occurs when an inbound event from another system automatically starts an agent run. This may include a new ticket, inbound email, status callback, chat application event, customer relationship management update, or other webhook-driven workflow.

This deployment pattern creates an elevated exposure condition because the agent may run without a human reviewing the event first. The event payload may contain free text, metadata, links, attachments, or structured fields that the synthetic subject treats as task context.

The primary risk is attacker-shaped event input. Public or weakly authenticated endpoints may allow an external actor to forge, replay, or manipulate event payloads. A single malicious event may then trigger downstream actions, such as ticket routing, message generation, record updates, external calls, or tool execution, before anyone notices.

Investigators should review the event source, webhook authentication, payload content, replay protections, trigger rules, agent run logs, tool calls, downstream actions, and output destinations. Particular attention should be given to forged or repeated events, unusual payload fields, newly observed sources, and actions that exceed the normal event workflow.

Investigative Relevance

Webhook event triggers are relevant because they allow external or third-party system events to initiate agent behavior without direct human oversight. The workflow may appear routine, while the effective instruction is carried in the event payload.

This sub-section is especially relevant where agents process inbound webhooks, status callbacks, chat events, ticket events, email events, customer updates, integration messages, or other automated triggers from public, partner, or weakly trusted systems.

A batch processing trigger occurs when an agent or model processes queued rows, files, records, or items in a scheduled data pipeline. This may include Extract, Transform, Load (ETL) jobs, bulk classification runs, document processing queues, ticket enrichment, record summarization, or scheduled workflow automation.

This deployment pattern creates an elevated exposure condition because each item is processed without per-item human review. A single poisoned row, file, record, or queued item may enter the model’s context and influence the run while appearing to be ordinary batch input.

The primary risk is hidden manipulation inside routine throughput. Because the run is bulk and scheduled, a tampered item may be difficult to distinguish from normal processing. If the agent has broad pipeline permissions, one poisoned record may trigger outputs, updates, classifications, external calls, or downstream actions across the job’s full data scope.

Investigators should review the pipeline directive, schedule, input queue, source records, transformation logs, model outputs, tool calls, downstream writes, error handling, and affected data scope. Particular attention should be given to anomalous individual records, repeated harmful outputs across a backlog, externally sourced rows or files, and changes that occurred without per-item approval.

Investigative Relevance

Batch processing triggers are relevant because they allow a synthetic subject to act across many records at machine speed with limited human visibility. A harmful instruction or manipulated input may be hidden inside otherwise normal pipeline activity.

Poisoned tool description occurs when a connected tool’s description, metadata, schema, or usage instructions contain hidden or adversarial instructions that influence the synthetic subject. These instructions may be visible to the model during tool selection but hidden, truncated, or unclear to the human reviewer.

This configuration creates an elevated exposure condition because tool descriptions are not passive documentation. They may enter the model’s context and affect which tool is selected, what data is passed to it, and how the synthetic subject behaves before or after the call.

The primary risk is metadata-driven manipulation. A synthetic subject may disclose secrets, call unsafe tools, pass sensitive data, or perform unauthorized actions because the tool description instructs it to do so.

Investigators should review tool descriptions, metadata, schemas, client display behavior, hidden text, encoded content, prompt-like language, and tool-call logs. Particular attention should be given to descriptions containing instructions to ignore rules, access sensitive files, forward data, or prefer one tool over another.

Investigative Relevance

Poisoned tool descriptions are relevant because the attack surface may sit in tool metadata rather than user prompts or tool code. This sub-section is especially relevant where tools are installed from marketplaces, open registries, third-party repositories, or MCP servers managed outside the organization.

Cross-tenant content injection occurs when content authored in one tenant, organization, or external customer environment is processed by an embedded artificial intelligence feature in another. This may occur through shared Software as a Service (SaaS) platforms, customer relationship management records, support tickets, shared documents, partner portals, email threads, comments, or other collaborative surfaces.

This deployment pattern creates an elevated exposure condition because a malicious actor does not need direct access to the victim’s tenant or agent. They only need to place content into a shared surface that the embedded synthetic subject later reads, summarizes, classifies, routes, or acts upon.

The primary risk is cross-boundary instruction execution. A malicious instruction may travel as ordinary business content from one party to another, then execute when the receiving party’s embedded agent processes it. The resulting action may occur under the victim organization’s SaaS tenant, service identity, or employee workflow, even though the effective instruction originated externally.

A related risk is attribution failure. The malicious payload and the executing agent belong to different parties, while the shared SaaS provider may only see normal platform activity. Victim logs may show the agent processing a legitimate record, and vendor logs may show permitted tenant behavior, making origin, authorization, and responsibility difficult to establish.

A further risk is shared-service data exposure. Where the vendor uses a shared artificial intelligence service across multiple customers, confidential data submitted by one customer may be processed, indexed, retained, or reused in a way that affects another customer’s environment. This can expose proprietary information, customer data, regulated records, or privileged material through generated answers, shared context, model memory, retrieval results, telemetry, or vendor-managed integrations.

Investigators should review the shared SaaS surface, source tenant or external origin, record history, embedded content, agent processing logs, tenant audit records, vendor logs, downstream actions, and shared-service data handling. Particular attention should be given to externally authored fields, cross-tenant records, shared documents, support tickets, partner inputs, unexpected tenant-to-tenant data exposure, and actions triggered without direct authentication by the external originator.

Investigative Relevance

Cross-tenant content injection is relevant because it allows an external party to influence a synthetic subject through ordinary shared business content. Standard authentication may not prevent the attack because the injected instruction enters through a legitimate collaboration or customer channel.

This sub-section is especially relevant where embedded artificial intelligence features process records, tickets, documents, forms, comments, emails, or other content that crosses tenant, vendor, customer, partner, or organizational boundaries. It is also relevant where vendor-hosted artificial intelligence services process confidential data from multiple customers through shared infrastructure, shared retrieval systems, shared model services, or vendor-managed integrations.

Connect-time tool metadata invocation occurs when a synthetic subject is influenced by tool, connector, or Model Context Protocol (MCP) metadata at the moment the tool is made available. MCP is an integration pattern that allows a synthetic subject to discover and use external tools, data sources, and actions through a structured interface.

This invocation does not require the tool to be called. The triggering content may appear in the tool description, server instructions, schema, parameter text, tool list, or other metadata loaded into the synthetic subject’s context during connection or discovery. Once that metadata is visible to the model, it may function as an instruction source.

This creates an elevated exposure condition because the synthetic subject may change behavior before any observable tool execution occurs. A malicious or compromised connector may instruct the synthetic subject to prefer a certain tool, ignore competing tools, request sensitive data, disclose information, alter its reasoning, or prepare a later action before the operator has approved any tool call.

The primary risk is line jumping. The connector-supplied metadata enters the instruction context ahead of the normal approval point, allowing it to influence the synthetic subject before a human reviews a specific action. Human approval may then become ineffective because the synthetic subject has already been steered by the metadata it received at connection time.

A related risk is metadata drift. A tool or server may appear safe when first approved, then later change its description, schema, server instructions, or metadata. If those changes are not detected and re-approved, an already trusted connector can become a new invocation source without a new user prompt or tool execution.

Investigators should review the exact tool metadata loaded into context, tool descriptions, server instructions, schema fields, connector version history, MCP server responses, approval records, tool-list payloads, hidden characters, and behavior changes following connection. Particular attention should be given to instruction-like metadata, invisible Unicode, changed descriptions, cross-server tool shadowing, and behavioral shifts that correlate with connector enrollment rather than a user prompt.

Investigative Relevance

Connect-time tool metadata invocation is relevant because the triggering instruction may enter the synthetic subject before any tool use appears in ordinary logs. An investigation that reviews only executed tool calls may miss the earlier metadata that caused the synthetic subject to behave differently.

This section is especially relevant where synthetic subjects connect to MCP servers, plugins, marketplace tools, internal connectors, tool registries, tool discovery endpoints, or dynamically supplied function definitions.

Hidden terminal-control invocation occurs when a Model Context Protocol (MCP) server supplies tool metadata or tool output containing terminal control sequences that alter what the human operator sees while still leaving instruction-bearing content visible to the synthetic subject. MCP is an integration pattern that allows a synthetic subject to discover and use external tools, data sources, and actions through a structured interface.

This invocation creates an elevated exposure condition because the human-visible display and the model-visible context may diverge. A malicious MCP server may use American National Standards Institute (ANSI) escape codes to hide, overwrite, erase, recolor, or disguise instructions in terminal output. The operator may see benign tool output, while the synthetic subject receives and acts on hidden instructions.

The primary risk is display-layer deception leading to synthetic subject action. A hidden instruction may cause the synthetic subject to recommend malicious package sources, alter code, disclose environment variables, create a backdoor, follow a phishing link, or perform another action that appears unrelated to the visible output. The instruction is not issued directly by the operator, but by content rendered through the MCP tool or server.

A related risk is review failure. Human-in-the-loop controls may be weakened because the reviewer is not evaluating the same content that the synthetic subject received. If tool descriptions or outputs are rendered with terminal formatting, cursor movement, screen clearing, or deceptive hyperlinks, a diligent operator may still miss the effective instruction.

Investigators should review raw MCP tool descriptions, raw tool outputs, terminal logs, rendered output, ANSI escape sequences, hidden Unicode, cursor-control characters, hyperlink escape sequences, tool-call history, and subsequent synthetic subject actions. Particular attention should be given to differences between raw and rendered content, invisible text, overwritten terminal lines, cleared-screen sequences, deceptive hyperlinks, and behavior changes following MCP output.

Investigative Relevance

Hidden terminal-control invocation is relevant because the triggering instruction may be concealed at the display layer rather than in the semantic content alone. The investigation must compare what the synthetic subject received with what the human operator could actually see.

This sub-section is especially relevant where synthetic subjects operate through command-line MCP clients, developer terminals, coding agents, local tool servers, security tools, package-management workflows, or any environment where tool output is rendered in a terminal.

MCP tool-output invocation occurs when output returned by a Model Context Protocol (MCP) tool causes a synthetic subject to act. MCP is an integration pattern that allows a synthetic subject to discover and use external tools, data sources, and actions through a structured interface.

This invocation occurs after a tool call, when the tool result is returned to the synthetic subject’s context. The output may contain ordinary data, but it may also contain instruction-bearing content that causes the synthetic subject to call another tool, disclose information, alter its plan, or continue a workflow in an unsafe direction.

The primary risk is tool-returned instruction execution. A compromised, malicious, or attacker-influenced MCP tool may return content that the synthetic subject treats as a command rather than as data. This is especially significant where the tool processes web pages, files, tickets, customer records, repository content, database results, or other low-trust sources.

Investigators should review raw tool outputs, tool-call logs, returned content, subsequent tool calls, prompt and response records, and downstream actions. Particular attention should be given to instructions embedded in tool results, external content returned by tools, repeated tool-call chains, and actions that began only after a specific tool output entered context.

Investigative Relevance

MCP tool-output invocation is relevant because tool results can become an instruction source after the operator has already approved or initiated a tool call. The investigation must determine whether the synthetic subject acted on the requested tool result or on instructions embedded inside that result.

This sub-section is especially relevant where MCP tools retrieve webpages, read files, query databases, summarize tickets, inspect repositories, fetch external resources, or return model-visible text from untrusted or mixed-trust sources.

MCP resource content invocation occurs when content exposed through an MCP resource causes a synthetic subject to act. MCP resources allow servers to expose contextual data, such as files, documents, records, repository content, logs, or other readable material, to the client and model context.

This invocation creates an elevated exposure condition because resource content may be treated as task-relevant context while also carrying embedded instructions. A resource may appear to be a document, file, record, or data object, but contain prompt-like text that directs the synthetic subject to ignore rules, call tools, disclose information, or change behavior.

The primary risk is resource-borne instruction execution. A malicious or low-trust resource may be read as data, but used by the synthetic subject as an instruction source. This is especially significant where MCP resources expose external files, shared folders, repository content, user-submitted records, logs, or other material that may be modified by untrusted parties.

Investigators should review MCP resource reads, raw resource content, source provenance, access permissions, retrieved records, prompt and response logs, and actions following resource access. Particular attention should be given to instruction-like text in resources, hidden or obfuscated content, externally writable resources, and actions that follow resource reads rather than operator prompts.

Investigative Relevance

MCP resource content invocation is relevant because resources can introduce instructions through a data channel rather than a tool description or direct prompt. The synthetic subject may appear to be reading context, while the effective instruction is embedded inside that context.

This sub-section is especially relevant where MCP servers expose filesystems, repositories, documentation stores, ticket systems, customer records, logs, emails, or other resources that may include untrusted or externally influenced content.

MCP prompt template invocation occurs when a prompt template supplied by an MCP server causes a synthetic subject to act. MCP prompt templates allow servers to provide structured messages and instructions for interacting with language models. Prompt templates can provide reusable instructions, workflows, or task structures that are exposed by a server and made available to the user or client.

This invocation creates an elevated exposure condition because a server-supplied prompt may carry instructions that appear operationally legitimate. The prompt template may define the task, request inputs, structure the workflow, select tools, or frame what the synthetic subject should do next.

The primary risk is server-supplied task steering. A malicious or compromised MCP prompt template may cause the synthetic subject to request sensitive data, invoke unsafe tools, disclose context, bypass policy, or route work through attacker-controlled resources while appearing to follow a normal workflow.

Investigators should review MCP prompt templates, prompt arguments, template provenance, server ownership, prompt version history, user selections, resulting model prompts, and downstream tool calls. Particular attention should be given to prompt templates that request secrets, route data externally, override standing instructions, or cause tool use beyond the apparent task.

Investigative Relevance

MCP prompt template invocation is relevant because the instruction source may be a reusable prompt supplied by a server rather than a direct user instruction. The operator may select a prompt template without understanding the full model-visible instruction it contains.

This sub-section is especially relevant where MCP servers expose slash-command-style workflows, reusable prompts, coding templates, investigation templates, automation prompts, or task-specific prompt libraries.