cs-create-prd

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses codespring CLI tools and bash to interact with the local development environment and the CodeSpring platform. It retrieves project configuration from .codespring/config.json and updates the project's mindmap nodes.
  • [DATA_EXPOSURE]: It deep-dives into the codebase to document architecture, API routes, data models, and environment variables. While it accesses sensitive architectural information, this is required for the primary function of generating accurate technical specifications.
  • [EXTERNAL_DOWNLOADS]: The skill employs npx to run @codespring-app/cli, ensuring it uses the official tools provided by the vendor. This is a standard practice for this platform's integration.
  • [DATA_EXFILTRATION]: Network requests are made via curl to the CodeSpring API to transmit generated documentation. These operations are directed to the vendor's own infrastructure and serve the skill's documented intent.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted codebase content. However, this is an inherent characteristic of documentation tools and is considered safe in this context. (Ingestion: Local codebase files; Boundaries: None; Capabilities: CLI execution and API sync; Sanitization: None mentioned).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 09:20 AM
Security Audit — agent-trust-hub — cs-create-prd