to-issues
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill follows standard software development practices for breaking down tasks into issues. No high-risk commands, credential exposure, or persistence mechanisms were found.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from issue trackers and project documents.\n
- Ingestion points: Reads full bodies and comments from the issue tracker as described in Step 1 of SKILL.md.\n
- Boundary markers: None identified in the provided instructions.\n
- Capability inventory: Publishing new issues to an issue tracker based on templates in Step 5.\n
- Sanitization: None identified; however, the impact is low as the output is restricted to new issue creation.
Audit Metadata