intellexer-api

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly lists actions that fetch and process arbitrary public URLs (e.g., "parse-document-url", "summarize-url", "get-topics-from-url", "compare-urls") and documents the use of the Membrane proxy via membrane request to retrieve external content, so the agent will ingest untrusted third-party web content that can influence downstream actions.