extension-authoring

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a pure documentation resource focused on extension development and does not contain any executable code.
  • [SAFE]: The documentation includes dedicated security sections such as a "Security Checklist" and "Tool Security" guidelines, promoting best practices like the principle of least privilege.
  • [SAFE]: Command examples (e.g., git status, npm test, osascript) are purely illustrative and use placeholders or safety spacing (e.g., "! git") to prevent accidental execution during the skill's loading process.
  • [SAFE]: The skill provides explicit guidance on mitigating indirect prompt injection and ensuring path safety when authoring automation hooks and subagents.
  • [SAFE]: No obfuscation, data exfiltration, persistence mechanisms, or unauthorized remote code execution patterns were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 06:50 PM