twitter-thread-writer

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

• Third-party content exposure detected (high risk: 1.00). This skill's Step 1 ("Research the Product and Angle") explicitly instructs the agent to run web_search queries (e.g., web_search "[product name] best features use cases" and web_search "site:twitter.com [product name] affiliate") to ingest public web pages and user-generated Twitter content and then use those findings to shape thread content and actions, which clearly exposes the agent to untrusted third‑party content that can influence its decisions.