broken-link-checker

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The required checker script (scripts/checker.py) and the SKILL.md "Run the Scan" step instruct the agent to crawl and fetch public web pages starting from a user-provided URL, parsing HTML to extract and evaluate links from arbitrary third‑party sites, so untrusted web content is ingested and directly drives the tool's results and subsequent recommendations.