map-the-landscape

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

• Third-party content exposure detected (low risk: 0.10). The skill’s workflow only instructs the agent to read the target repository’s own files/local documentation and, for topic claims, to browse and cite authoritative external sources; it does not describe ingesting outsider-authored free text from a continuously monitored queue/feed (e.g., email/chat/tickets) as an input channel.