cloud-saas-exposure

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow ingests outsider-authored free text by reading bucket/listing bodies and object-key strings from HTTP GET/Listing responses in its storage-bucket discovery (§6), where those response bodies are authored by third parties (bucket owners) and then parsed/triaged by the agent.