specrail-pr-gate
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill automates PR quality checks by instructing the agent to run local Python scripts (
checks/github_pr_evidence.pyandchecks/pr_gate.py). These operations are used for evidence gathering and policy evaluation, which aligns with the stated purpose of the skill. No malicious command injection, data exfiltration, or credential harvesting patterns were found. The instructions explicitly include safety boundaries that prevent the agent from performing unauthorized merge operations or ignoring unresolved review threads.
Audit Metadata