github-issue
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with untrusted external content from GitHub issues and comments, which constitutes a potential attack surface. However, the skill provides comprehensive defensive instructions to mitigate this risk. Ingestion points: Title, body, and comments of GitHub issues (referenced in SKILL.md and references/metadata-and-projects.md). Boundary markers: Explicit instructions in SKILL.md and evals/github-issue.json mandate ignoring hostile instructions. Capability inventory: Uses the GitHub CLI (gh) to view and edit issues (SKILL.md). Sanitization: Advises removing secrets before publication and human verification (SKILL.md).
Audit Metadata