manage-skills

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides automated workflows for creating and executing local scripts (Bash, Python, Node.js) and managing file permissions (e.g., chmod +x) within the skill's directory. This is used to facilitate setup and deployment tasks for the user.
  • [DATA_EXFILTRATION]: The skill reads local skill files and configurations to perform audits and verification. It also uses platform tools like WebSearch and Context7 to verify the accuracy of external technical claims.
  • [SAFE]: The skill incorporates significant security-focused content. The references/api-security.md file teaches users how to handle API keys safely using wrapper scripts and local environment files to avoid leaking secrets into chat logs. Additionally, references/common-patterns.md warns against the security risks associated with dynamic context syntax (!) and provided mitigations.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 11:38 AM