mission-doc-route
Pass
Audited by Gen Agent Trust Hub on May 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and processes external markdown documents to determine execution logic. An attacker could embed instructions within a document to mimic user approval or manipulate the routing logic.
- Ingestion points: The skill is designed to read and evaluate the contents of
.mdfiles provided as input (described inSKILL.mdunder Step 1 and Step 2). - Boundary markers: The instructions lack explicit boundary markers or directives to the agent to disregard instructions embedded within the processed document content.
- Capability inventory: The skill has the capability to delegate tasks to other high-impact tools like
mission-approved-docandmission-long-taskbased on document analysis. - Sanitization: There is no evidence of content sanitization, validation, or escaping of the ingested document content before it is used to influence the agent's decision-making process.
Audit Metadata