bluesky

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

• Third-party content exposure detected (high risk: 0.90). The skill uses the AT Protocol endpoints (e.g., the "https://bsky.social/xrpc/app.bsky.feed.searchPosts" and "app.bsky.actor.getProfile" calls) to fetch and read public Bluesky posts and profiles (user-generated, untrusted third‑party content) which the agent is expected to interpret as part of its workflow, enabling indirect prompt injection.