Agent Coordination

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and listens to network.comind.signal records and posts (e.g., "uv run python -m tools.coordination list/query", "listen", and mention_listener.py" and references to at://... app.bsky.feed.post/...), which are user-generated, public ATProtocol content the agent will read and act on, exposing it to untrusted third-party input that could carry indirect prompt injection.