account-research

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly "always" runs web searches and ingests content from public third‑party sites (e.g., company homepages, recent news articles, LinkedIn profiles and job/career pages) which are untrusted user- or third‑party–generated sources that the agent reads and synthesizes as part of its workflow.