new-api-support

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

• Third-party content exposure detected (high risk: 0.80). The workflow's Step 2 explicitly instructs the agent to "use web search" and consult public sources like Apple documentation, WWDC sessions, tutorials and Stack Overflow to research usage patterns, which requires fetching and interpreting untrusted, user-generated third‑party content that can influence testing and implementation decisions.