threads-api

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

• Third-party content exposure detected (high risk: 1.00). The skill includes examples and workflows that fetch and process user-generated social media content from Meta's Threads API (e.g., GET https://graph.threads.net/v1.0/me/threads and profile endpoints), meaning the agent would read arbitrary third-party posts and profiles that could carry indirect prompt injection.