triaging-issues

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious behavior or unsafe commands detected. The skill is designed for read-only analysis of project issues and PRs.
  • [PROMPT_INJECTION]: The skill processes untrusted content from GitHub issues and pull requests, which establishes a surface for indirect prompt injection.
  • Ingestion points: The skill reads issue descriptions, comments, and PR diffs using gh issue view and gh pr view.
  • Boundary markers: There are no explicit instructions or delimiters used to ignore or isolate instructions embedded within the untrusted issue/PR content.
  • Capability inventory: The skill utilizes the gh CLI for data retrieval but explicitly forbids write operations such as edit, close, or merge.
  • Sanitization: No input sanitization or validation is specified for the external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 07:44 PM