a2a-error-handling

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

• Third-party content exposure detected (high risk: 1.00). The "Before writing code" steps explicitly require fetching live docs from https://a2a-protocol.org/latest/specification/ and web-searching public GitHub (site:github.com a2aproject ...) and SDK docs, i.e., ingesting open/public third-party content that the agent must read and use to determine error-handling behavior, which could allow indirect prompt injection.