triage-pr-comments

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes development tools like gh, git, and jq. It correctly prevents command injection when handling external PR comment data by using jq --arg and pipe-based input for API calls.
  • [PROMPT_INJECTION]: The skill processes untrusted PR comments, representing an indirect prompt injection surface. The risk is minimized by the skill's structure, which uses the data for analysis and includes a human-mediated 'Step 4' to re-verify findings before any code modifications occur.
  • [DATA_EXFILTRATION]: Data access is limited to the targeted GitHub repository via authenticated CLI tools. There is no evidence of unauthorized local file access or unexpected network communication.
  • [EXTERNAL_DOWNLOADS]: The skill uses local CLI tools and does not perform unverified remote script execution or downloads from untrusted sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 07:22 PM
Security Audit — agent-trust-hub — triage-pr-comments