Skills
▥NYC
skills/shipshitdev/library/gh-address-comments/Gen Agent Trust Hub

gh-address-comments

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): Indirect prompt injection surface detected. 1. Ingestion points: Pull request and issue comments retrieved via gh api calls in SKILL.md. 2. Boundary markers: Absent; no specific delimiters are used to separate external content from agent instructions. 3. Capability inventory: The skill can modify code and post replies via the gh CLI. 4. Sanitization: Absent; the skill summarizes and proposes fixes based directly on external input.
  • COMMAND_EXECUTION (SAFE): The skill uses official GitHub CLI commands (gh auth, gh pr view, gh api) to perform intended tasks, which does not constitute unauthorized command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:32 PM