skills/pokanop/ai/idea-to-prd/Gen Agent Trust Hub

idea-to-prd

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted codebase data like package.json and pyproject.toml to align documentation with existing conventions, creating a surface where malicious file content could influence agent behavior.
  • Ingestion points: User-provided product ideas and project metadata files such as package.json, pyproject.toml, or lockfiles.
  • Boundary markers: None explicitly defined for the ingestion of codebase context.
  • Capability inventory: Capability to trigger shell commands found in the project's scripts via the agent's environment.
  • Sanitization: None specified for file ingestion.
  • [COMMAND_EXECUTION]: The skill instructs the agent to discover and run local project scripts (e.g., npm run test, pytest) for linting, testing, and building as part of a mandatory validation phase. This leads to the execution of commands that are defined within the user's local project configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 02:54 AM
Security Audit — agent-trust-hub — idea-to-prd