design-doc-reviewer
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a shell command to run a Python script located at
design-to-issues/scripts/story_contract.py. This script is intended for structural and mechanical validation of the design documents being reviewed.\n- [DYNAMIC_EXECUTION]: The skill resolves and executes a Python script from a local directory relative to the workspace. This is a standard project-specific execution pattern for internal tooling.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests and reviews untrusted external content such as PRDs and design specifications, which constitutes a surface for indirect prompt injection.\n - Ingestion points: The
<design-doc>provided by the user.\n - Boundary markers: The instructions do not specify explicit delimiters or 'ignore' instructions to isolate document content from the agent's task instructions.\n
- Capability inventory: The skill has capabilities to read repository files, execute a local script, and write output files to the
docs/design/reviews/directory.\n - Sanitization: There are no instructions for sanitizing or escaping the content of the documents being processed.
Audit Metadata