synthesize

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and processes arbitrary web and search results (see the queue "sources" entries with "url" and "search" types and the Extractor Prompt Template that says "Use WebFetch to retrieve: [URL]" and "Use WebSearch ... then WebFetch"), so it will read and interpret untrusted public third‑party content as part of its workflow.