intellexer-api

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly exposes the agent to arbitrary third-party web content via URL-based actions such as "parse-document-url", "summarize-url", "get-topics-from-url", and "recognize-named-entities-url", meaning the agent will fetch and interpret untrusted public webpages whose content could influence subsequent analysis or actions.