sap-cloud-sdk-ai

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

• Third-party content exposure detected (high risk: 0.90). The skill's agentic/workflow examples explicitly fetch and ingest public third-party content (e.g., fetch to https://api.open-meteo.com in references/agentic-workflows.md, loading MCP tools via loadMcpTools in the same file, and document-grounding/retrieval from external/vector/website sources in references/orchestration-guide.md and references/ai-core-api-guide.md), and those external results are read and used as context/tool outputs that can change subsequent tool calls and agent decisions.