gh-issue-drafter
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to generate GitHub issue content, creating a surface for potential indirect prompt injection.
- Ingestion points: User-provided text describing the "rough intent" for a new issue.
- Boundary markers: The skill requires an explicit user approval step where the drafted issue is presented for review before any repository modifications occur.
- Capability inventory: Uses the
ghCLI tool for repository metadata retrieval, label management, and issue creation. - Sanitization: The skill relies on human-in-the-loop verification of the generated content to mitigate the risk of processing malicious instructions.
Audit Metadata