ln-600-docs-auditor
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines various shell commands for the agent to execute, such as grep, ls, and wc, to verify documentation accuracy against the codebase and check for verbose patterns. Evidence: Quick Audit Commands in references/audit_checklist.md.
- [EXTERNAL_DOWNLOADS]: The diagram.html file loads the Mermaid.js visualization library from the JSDelivr CDN (cdn.jsdelivr.net), which is a well-known and trusted technology service.
- [PROMPT_INJECTION]: The skill analyzes project documentation files, creating a surface for indirect prompt injection where maliciously crafted content could influence agent behavior. (1) Ingestion points: All project Markdown files including CLAUDE.md, README.md, and documents in the docs/ directory. (2) Boundary markers: No explicit delimiters or ignore instruction directives are provided for the document content. (3) Capability inventory: The agent has the capability to read local files and execute shell-based search commands. (4) Sanitization: No content filtering or validation is performed on the documentation before it is processed.
Audit Metadata