viral-thread-generation

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly calls social-media fetch tools (x_search_tweets, x_get_tweets, x_get_profile, x_get_followers) in the MCP Tools section and Workflow steps 1–3 to ingest and analyze public tweets, profiles, and follower bios (untrusted, user-generated content) which the agent is expected to read and use to drive thread-topic selection and drafting, creating clear opportunity for indirect prompt injection.