external-pr-viability

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill utilizes the official GitHub CLI (gh) to perform read-only queries of public repository information, specifically PR merge history and organization membership. These operations are conducted against a well-known service and do not involve sensitive data exfiltration or unauthorized access.
  • [INDIRECT_PROMPT_INJECTION]: The instructions involve reading external content like CONTRIBUTING.md and README.md from third-party repositories. While this is a data ingestion surface, the skill is purely analytical and does not provide an execution path for malicious instructions contained within those files.
  • [COMMAND_EXECUTION]: The commands listed (gh pr list, gh api) are standard development tools used for their intended purpose of information gathering. No dangerous shell injection or privilege escalation patterns were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 05:53 AM
Security Audit — agent-trust-hub — external-pr-viability