enable-feedback-hooks
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes an initialization script and configures a post-session hook to run a Python script from the vendor's local cache directory (~/.claude/plugins/cache/product-forge-marketplace/).
- [PROMPT_INJECTION]: The feedback capture mechanism uses a prompt to analyze session history (untrusted data) without boundary markers or sanitization. Ingestion point: Full session history is processed by the analysis prompt. Boundary markers: None used in the prompt template. Capability inventory: The prompt output is processed by a subsequent Python script execution. Sanitization: No filtering of session content is performed before analysis.
Audit Metadata