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 includes agentic workflow and grounding examples that fetch and ingest public third‑party content into the agent's prompts and tool flow (e.g., the travel-agent tool fetches https://api.open-meteo.com in references/agentic_workflows.md, and document grounding/RetrievalApi usage and help.sap.com/SharePoint pipelines in references/orchestration-guide.md and references/ai-core-api-guide.md), so untrusted external content is read and can materially influence tool calls and next actions.