cloud-api-integration

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

• Third-party content exposure detected (high risk: 1.00). The skill includes explicit examples that fetch and ingest external documents/URLs (e.g., "Common Mistakes" showing fetch_url(url) and references/security-examples.md with fetch_document(url) / "Analyze the following UNTRUSTED document"), meaning the agent is expected to read and interpret untrusted, user-controlled third‑party content as part of its workflow.