ln-114-frontend-docs-creator

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is configured to fetch missing shared reference files from the author's repository at https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/. This is a vendor-owned resource used for retrieving static skill dependencies.
  • [PROMPT_INJECTION]: The skill presents an indirect injection surface as it ingests data from local project files (e.g., package.json, tailwind.config.js, and CSS files) to populate documentation templates. It mitigates risk through a strict NO_CODE_EXAMPLES rule that forbids the inclusion of CSS or component code in the output and employs validation steps to ensure no template markers or unauthorized content remain in the final document.
  • Ingestion points: Reads project configuration files (package.json, tailwind.config.js), CSS variables, and input from the ln-110 coordinator skill.
  • Boundary markers: Uses {{PLACEHOLDER}} syntax within markdown templates to delimit interpolated data.
  • Capability inventory: Limited to reading configuration files and writing markdown documentation files to the project directory.
  • Sanitization: Includes a mandatory rule prohibiting code blocks in output and performs self-validation to check for forbidden placeholders and metadata leaks.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 03:05 PM