bluesky-cascade-fetch

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

• Third-party content exposure detected (high risk: 0.90). The skill's required runtime fetch (scripts/bluesky_cascade_fetch.py and SKILL.md) calls public Bluesky XRPC endpoints (e.g., https://public.api.bsky.app via app.bsky.feed.searchPosts and app.bsky.feed.getPostThread) to ingest user-generated social posts and threads, and the agent parses and uses that content to decide pagination, which threads to expand, and downstream outputs—exposing it to untrusted third-party content that can influence actions.