scrape

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly scrapes arbitrary webpages via the Bright Data Web Unlocker (see SKILL.md usage and scripts/scrape.sh which POSTs an arbitrary "url" to https://api.brightdata.com/request), so it ingests untrusted public web content as part of its workflow and that content could influence agent actions.