interacting-with-agents

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches public agent cognition from comind.network (see the httpx.get call to https://comind.network/xrpc/com.atproto.repo.listRecords) and references public social handles (e.g., @violettan.bsky.social), so it ingests untrusted, user-generated third-party content as part of its workflow.