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/**/*, andREADME.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