azure-ai-projects-ts

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md Agents section (Agent Tools / Web Search example) explicitly includes a web_search_preview tool and instructions ("You can search the web to find current information") which cause the agent to fetch and ingest public web content that can influence its responses and actions, exposing it to untrusted third‑party content.