plugin-script-architecture

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a 'knowledge' mode resource containing only documentation and standards, with no executable code or scripts.
  • [SAFE]: Explicitly prohibits third-party Python dependencies in marketplace scripts, establishing a secure baseline that avoids external supply chain vulnerabilities.
  • [REMOTE_CODE_EXECUTION]: Outlines patterns for dynamic module resolution via 'importlib' for local internal helpers, which is a documented architectural feature of the system.
  • [COMMAND_EXECUTION]: Provides guidelines for the appropriate use of 'subprocess.run' when interacting with external tools like Git, Maven, and NPM.
  • [DATA_EXFILTRATION]: Describes standard procedures for accessing local project configuration data within the '.plan' directory and 'marshal.json' files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 07:13 AM
Security Audit — agent-trust-hub — plugin-script-architecture