joule-a2a-agent

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

• Third-party content exposure detected (high risk: 0.90). The skill scaffolds agent tools that call arbitrary external APIs and URLs (e.g., src/tools.ts and the example SAP OData / example_api_call in references/langgraph-a2a-agent-typescript.md and app/tools.py in the Python templates which perform fetch/httpx requests to external endpoints) and the agent is designed to read and act on those responses as part of its workflow, so untrusted third‑party content can influence agent decisions and tool use.