roadmap
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted GitHub issue content which may contain instructions to bypass agent guidelines.\n
- Ingestion points: Issue titles and bodies are fetched via the GitHub CLI in
references/sync.md,references/generate.md, andreferences/status.md.\n - Boundary markers: The skill uses a
CONTEXT.mdfile to define technical and project boundaries, providing a baseline for acceptable recommendations, though it does not explicitly delimit untrusted input strings.\n - Capability inventory: The skill can modify repository labels, edit issues, and write to local markdown files.\n
- Sanitization: No specific input sanitization or instruction-bypass protection is applied to the fetched GitHub data.
Audit Metadata