olostep

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

• Third-party content exposure detected (high risk: 1.00). The skill's endpoints (e.g., Create Scrape /v1/scrapes, Create Answer /v1/answers, Start Crawl /v1/crawls, Maps /v1/maps, and Retrieve Content /v1/retrieve) explicitly fetch and have the AI read arbitrary public web pages/URLs, which are untrusted third‑party/user‑generated content that can influence agent actions.