a2a-agent-card

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

• Third-party content exposure detected (high risk: 0.80). The skill's "Before writing code" steps explicitly instruct fetching live public documentation (e.g., https://a2a-protocol.org/latest/specification/) and web-searching GitHub for agent-card examples, meaning the agent will ingest and act on untrusted third-party content that can influence implementation and behavior.