claude-md-link-check
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill's behavior is consistent with its stated purpose of link validation.
- [COMMAND_EXECUTION]: The skill utilizes restricted Bash commands (find, test, ls) to locate documentation files and verify the existence of linked targets. These operations are scoped to file system discovery and existence checks.
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from documentation files. 1. Ingestion points: CLAUDE.md and .claude/rules/*.md files. 2. Boundary markers: Absent. 3. Capability inventory: Read, Glob, Grep, find, test, ls. 4. Sanitization: Absent. The risk is negligible as the skill only performs existence checks on extracted paths and does not execute external content or perform network actions.
Audit Metadata