data-sleuth

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly instructs the agent to ingest and analyze social media exports and user data (see "Use when analyzing social media exports" and "When data is provided" plus the Output Format requiring "quotes, data points, timestamps"), which are untrusted, user-generated third‑party contents the agent would read and interpret as part of its workflow.