a2a-messages-parts

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Before writing code" steps explicitly require fetching live docs from https://a2a-protocol.org/latest/specification/ and web-searching GitHub (site:github.com a2aproject ...) and SDK docs—public, third-party sources that the agent is expected to read and use to determine message/part schemas and behavior, which could allow indirect prompt injection.