threads-expert

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

• Third-party content exposure detected (high risk: 0.90). The skill's docs and required workflow explicitly instruct using the Threads API to read/search public, user-generated content (see references/threads-api.md "Reading: User's Threads", "Reading: Replies", "Search" and oEmbed endpoints on graph.threads.net), which are untrusted third-party posts the agent would ingest and that could materially influence subsequent actions.