ln-112-project-core-creator

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches shared reference files and templates from the author's official GitHub repository (github.com/levnikolaevich/claude-code-skills) if they are missing locally. This behavior is documented for fetching configuration and templating resources.
  • [PROMPT_INJECTION]: The skill processes untrusted data from the project codebase and legacy documentation, creating an indirect prompt injection surface.
  • Ingestion points: Context store from the coordinator skill and local project files (SKILL.md).
  • Boundary markers: Uses specific markdown comments to identify the source of content, such as legacy migration or auto-detection markers (SKILL.md).
  • Capability inventory: Performs file read and write operations within the project directory to generate markdown documentation.
  • Sanitization: Employs a self-validation phase using 16+ specific questions and a documentation quality contract to ensure content validity (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 02:26 PM