ln-160-docs-skill-extractor

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted project documentation to generate new executable commands.
  • Ingestion points: Documentation sources like docs/**/*.md, tests/**/*, and README.md.
  • Boundary markers: The skill does not define specific delimiters for processed documentation content.
  • Capability inventory: Reads local files and creates new command files in the .claude/commands/ directory.
  • Sanitization: Content is classified based on patterns but not sanitized; however, a mandatory user approval gate (Phase 3) and an automated review (Phase 5) are implemented as safeguards.
  • [EXTERNAL_DOWNLOADS]: The skill attempts to fetch reference files and protocols from the author's GitHub repository (levnikolaevich/claude-code-skills) if they are missing locally.
  • [COMMAND_EXECUTION]: The skill creates new executable command files in the target project's .claude/commands/ directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 07:57 PM