to-issues
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external issue trackers which could contain instructions designed to influence the agent.
- Ingestion points: Fetches full bodies and comments of issue references in Step 1 of the process.
- Boundary markers: No delimiters or isolation instructions are defined for the fetched external content, although the human review in Step 4 acts as a manual check.
- Capability inventory: The skill has capabilities to read the codebase (Step 2) and write new issues to the tracker (Step 5).
- Sanitization: No sanitization, escaping, or filtering of external issue content is mentioned before processing.
Audit Metadata