backfilling-atproto

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

• Third-party content exposure detected (high risk: 0.90). This skill directly fetches and processes user-generated ATProto content from public third‑party endpoints (e.g., https://public.api.bsky.app, https://plc.directory/{did}, and PDS endpoints such as https://comind.network/xrpc/com.atproto.repo.listRecords), so it ingests untrusted third‑party content that could carry indirect prompt injections.