url-analysis

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

• Third-party content exposure detected (high risk: 0.80). The skill's validate_urls.py script (scripts/validate-urls.py) performs HTTP requests (requests.head) against arbitrary URLs supplied via --url or extracted from input files, and the skill's "Contextual Analysis" functionality explicitly evaluates destination content, meaning it fetches and interprets untrusted public web pages.