twitter-thread-creation

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

• Third-party content exposure detected (low risk: 0.10). The required posting workflow only writes user-supplied text to X, but the "Repurposing to Thread" section has the agent run a web search (tavily/search-assistant) and screenshot arbitrary URLs, which pulls in outsider-authored web content the agent must actively seek out, so this is low risk.