gs-council
Pass
Audited by Gen Agent Trust Hub on Nov 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided code and instructions by feeding them to three different external AI models for parallel review, creating an attack surface for indirect instructions.
- Ingestion points: Processes the user's current implementation and pull request context as described in
SKILL.md. - Boundary markers: No explicit delimiters or instructions are provided to the delegates to ignore potentially malicious instructions embedded in the code being reviewed.
- Capability inventory: The skill allows the agent to edit local files based on delegate recommendations and modify pull request descriptions.
- Sanitization: No sanitization or filtering of the code content is specified before passing it to sub-agents.
Audit Metadata