threads-api

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and process public, user-generated content from Meta Threads (e.g., graph.threads.net endpoints shown in "Fetching User's Threads", "Fetching User Profile" examples and the "User Data Retrieval Flow"), so untrusted third‑party posts could be read and materially influence actions.