Skills
skills/richfrem/agent-plugins-skills/link-checker-agent/Gen Agent Trust Hub

link-checker-agent

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill's design allows it to ingest content from repository files that could potentially contain malicious instructions intended to influence the agent's behavior.
  • Ingestion points: The scripts scripts/check_broken_paths.py and scripts/smart_fix_links.py recursively read all markdown and text files in the scanned directory.
  • Boundary markers: Absent. The skill does not use delimiters or instructions to isolate the documentation content from the agent's command context.
  • Capability inventory: The skill is granted Bash and Write capabilities in SKILL.md. The scripts scripts/smart_fix_links.py, scripts/map_repository_files.py, and scripts/check_broken_paths.py perform file-write operations to create maps, logs, and update documentation links.
  • Sanitization: Absent. The scripts do not validate or sanitize the content of the files they read before processing or rewriting them.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 06:49 PM