implement
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes local utility scripts using node (e.g., .agents/scripts/cooking.mjs and .agents/scripts/spec-files.mjs) to manage implementation states and validate specifications. It also executes repository-specific commands for linting, type-checking, and testing as defined in package.json or Makefile.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection through data ingestion. 1. Ingestion points: Reads contents from Pn.md, spec.md, reviews/Pn.md, and user-provided implementation descriptions. 2. Boundary markers: The instructions do not define explicit boundary markers or delimiters for the external content being processed. 3. Capability inventory: The skill can execute shell commands via local Node.js scripts and run test/lint suites, as well as modify project files. 4. Sanitization: There is no explicit sanitization or filtering logic mentioned for the ingested content.
Audit Metadata