triaging-visual-review-runs
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for triaging PostHog Visual Review runs using GitHub CLI and vendor-specific MCP tools. No unauthorized operations were found.
- [SAFE]: The skill includes explicit safety guardrails, notably the 'Finalize Gate', which prevents the agent from committing visual changes or greening merge gates without per-run human confirmation.
- [SAFE]: Use of command-line tools like
git,gh, andcurlis constrained to the intended purpose of code diffing and screenshot inspection. No exfiltration or credential access was detected. - [SAFE]: The skill explicitly warns against insecure practices like pushing fork heads to in-repo branches and correctly identifies the security boundaries of GitHub Actions secrets.
Audit Metadata