a2a-authentication

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

• Third-party content exposure detected (high risk: 1.00). The skill's "Before writing code" steps explicitly instruct the agent to fetch and web-search live public resources (e.g., https://a2a-protocol.org/latest/specification/ and site:github.com a2aproject) so the agent will read untrusted third-party web content that can influence implementation and behavior.