finalize-step-plugin-doctor

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill orchestrates a quality-control workflow by executing several internal scripts via a local Python executor ('.plan/execute-script.py'). These commands handle reading project metadata, managing status logs, and running the core linting tool.
  • [PROMPT_INJECTION]: The skill processes file paths provided by the system's reference manager to determine which directories require linting. This constitutes a surface for indirect prompt injection, as the agent's logic is influenced by the contents of the 'affected_files' list.
  • Ingestion points: The list of file paths is retrieved in Step 1 from the 'affected_files' field of the project references.
  • Boundary markers: None provided; the script relies on subsequent filtering logic.
  • Capability inventory: The skill has the ability to execute arbitrary internal tools via the 'execute-script.py' mechanism.
  • Sanitization: Step 2 applies regex-based filtering to ensure only paths within the 'marketplace' or '.claude/skills' directories are processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 07:12 AM
Security Audit — agent-trust-hub — finalize-step-plugin-doctor