analyse-issue
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from GitHub issues which could theoretically contain malicious instructions. 1. Ingestion points: The skill fetches issue titles, bodies, and comments from GitHub in SKILL.md. 2. Boundary markers: Absent; fetched content is processed directly. 3. Capability inventory: Can execute git, gh, rg, curl, and local tests as specified in SKILL.md. 4. Sanitization: Absent.
- [COMMAND_EXECUTION]: The skill relies on executing common developer system commands for its operation. Evidence: Explicitly uses git, gh, and rg in SKILL.md.
- [EXTERNAL_DOWNLOADS]: The skill retrieves issue content from an external source. Evidence: Uses the GitHub CLI (gh) and curl to fetch issue data from the GitHub API, which is a well-known service.
Audit Metadata