github-issue-pr-draft
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The skill follows best practices for secret management and user oversight.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted data from external sources.
- Ingestion points: The skill reads upstream issue and pull request templates, existing issue comments, and repository diffs during Step 2 and Step 3.
- Boundary markers: No explicit delimiters are specified to wrap ingested data in the instructions.
- Capability inventory: The agent can create or update issues and pull requests via GitHub tools.
- Sanitization: The skill performs log redaction for sensitive patterns but does not specifically sanitize text for embedded instructions.
- Mitigation: The risk is mitigated by a mandatory 'Confirmation Gate' (Step 4) and an 'IRON LAW' that prohibits any execution without explicit user review and approval of the final drafted content.
Audit Metadata