link-checker-agent
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides several Python scripts (map_repository_files.py, smart_fix_links.py, check_broken_paths.py) intended to be executed via the Bash tool to perform directory walking and file modification tasks.
- [SAFE]: The skill's behavior is consistent with its stated purpose. All operations are restricted to the local file system, targeting common documentation formats. No evidence of malicious behavior, data exfiltration, or credential harvesting was identified.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it reads and processes user-controlled repository files. Ingestion points: Markdown and text files read by the auditing scripts. Boundary markers: Absent; files are read directly for processing. Capability inventory: The skill can modify local markdown files. Sanitization: Content is parsed using regular expressions for link patterns but not for instructions. The risk is assessed as safe because the processed content is not executed or interpreted as instructions by the scripts.
Audit Metadata