ln-100-documents-pipeline

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches shared references and configuration files from the author's official GitHub repository (levnikolaevich/claude-code-skills) using the WebFetch tool if local directories are not detected.
  • [COMMAND_EXECUTION]: Executes a local JavaScript tool (shared/scripts/docs-quality/cli.mjs) using the node runtime to perform automated quality checks and generate documentation manifests.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests and processes untrusted repository files like README.md and CONTRIBUTING.md to extract facts for document generation.
  • Ingestion points: Project documentation files scanned during the legacy detection phase (Phase 0).
  • Boundary markers: While the skill mentions a quality gate (Phase 3) and verification steps, it does not explicitly define the use of delimiters or 'ignore' instructions for the extracted content inside prompts.
  • Capability inventory: Includes the ability to execute shell commands via node, modify the file system via Edit, and orchestrate other skills using the Skill tool.
  • Sanitization: Implements a quality verification phase that uses a verifier script to detect forbidden placeholders, broken links, and metadata leaks.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 01:34 PM