factory
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon external, potentially attacker-controlled data from GitHub issues and PRs, which could contain malicious instructions. \n
- Ingestion points: Reads issue contracts, comments, blockers, and handoff documentation in SKILL.md. \n
- Boundary markers: The instructions do not specify any markers or delimiters to separate data from instructions within the processed issue content. \n
- Capability inventory: The skill has the capability to trigger implement (code implementation) and babysit (validation and merging) across multiple workflow paths in SKILL.md. \n
- Sanitization: The skill does not mention any sanitization or validation of the input data before it is used to determine the agent's actions.
Audit Metadata