project-closeout
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, such as project agreements, financial records, and deliverable inventories, to generate closeout documentation. This creates an attack surface where instructions hidden within these documents could be followed by the agent.
- Ingestion points: The main instructions in SKILL.md require the agent to use supplied agreements and records.
- Boundary markers: The skill lacks instructions for the agent to use delimiters or to ignore embedded commands within the source documents.
- Capability inventory: The skill's primary function is generating reports and checklists; it does not define subprocess execution, file system modifications, or network requests.
- Sanitization: There are no instructions for sanitizing, escaping, or validating the input data before processing.
Audit Metadata