housekeeper
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes repository content and code projects which are untrusted external data sources. This creates a surface where malicious instructions could be embedded in code or comments to influence the agent.
- [INDIRECT_PROMPT_INJECTION]: Mandatory Evidence Chain: 1. Ingestion points: Repository or code project files (SKILL.md). 2. Boundary markers: No explicit markers are used to separate the agent's instructions from the analyzed code. 3. Capability inventory: Ability to modify project files, run builds, execute tests, and perform runtime checks. 4. Sanitization: The skill does not mention sanitizing or escaping the content of the files before processing them.
Audit Metadata