a2a-streaming

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches documentation from a-protocol.org and GitHub via search and fetch, representing low-risk external content retrieval.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs fetching specification content from an external website (a2a-protocol.org) to govern its behavior and implementation details, but lacks verifiable publisher provenance, placing it in the high-risk tier.