create-cowork-plugin

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • Standard Command Execution: The skill employs standard system utilities such as zip and cp to package the completed plugin into a .plugin archive and move it to the local outputs directory. These operations are essential for the skill's primary function of delivering a ready-to-use plugin file.
  • Secure Configuration Patterns: The documentation encourages the use of ${VAR_NAME} placeholders for MCP server configurations and intra-plugin paths. This approach is a recognized best practice for avoiding hardcoded secrets and maintaining portability across different environments.
  • Validation Procedures: The workflow includes a structural verification step, recommending the use of claude plugin validate or manual checks to ensure the plugin.json manifest and directory layout are correct before final packaging.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:17 AM
Security Audit — agent-trust-hub — create-cowork-plugin