ln-911-github-triager

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted community data from GitHub to generate triage reports.
  • Ingestion points: Untrusted content retrieved via gh issue list, gh pr list, and gh api graphql commands in SKILL.md.
  • Boundary markers: No delimiters or boundary markers are used to separate community-sourced data from the agent's instructions.
  • Capability inventory: The skill is restricted to Read and Bash (read-only queries) tools as defined in SKILL.md.
  • Sanitization: No sanitization or filtering of fetched GitHub content is performed before processing.
  • [EXTERNAL_DOWNLOADS]: The skill fetches missing shared strategy and configuration files from the author's GitHub repository (levnikolaevich/claude-code-skills).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 02:50 AM