Skills
Navigate
skills/paulkinlan/chrome-devrel-skill/chrome-devrel/Gen Agent Trust Hub

chrome-devrel

Fail

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: CRITICAL
Full Analysis
  • [PROMPT_INJECTION]: No behavior override attempts or bypass markers were detected. The skill instructions provide strict operational guidelines that prioritize evidence and accuracy.
  • [DATA_EXFILTRATION]: No sensitive file paths or credential harvesting patterns were found. The skill includes explicit instructions to preserve the public/private data boundary.
  • [COMMAND_EXECUTION]: No dangerous or autonomous command execution patterns. Documentation examples of shell commands are benign and intended for manual execution by developers.
  • [EXTERNAL_DOWNLOADS]: The skill references numerous external resources, all of which originate from trusted technical domains (e.g., GitHub, W3C, WHATWG, Chrome Status). The phishing alert for the immersive-web.github.io domain is a false positive, as it is the official site for the WebXR specification community group.
Recommendations
  • Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Jul 28, 2026, 06:43 PM