a2a-protocol
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements the A2A (Agent-to-Agent) protocol using standard architectural patterns. The provided examples for both Python and Node.js environments demonstrate expected behavior for building interoperable AI agents.
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
a2a-sdkvia pip and@a2a-js/sdkvia npm. These are standard library installations for the protocol being described and use well-known package registries (PyPI and npm). - [DATA_EXPOSURE_&_EXFILTRATION]: No sensitive file access or unauthorized network operations were identified. The protocol correctly uses
/.well-known/agent.jsonfor discovery as per industry standards for metadata exposure. - [PROMPT_INJECTION]: No attempts to override agent behavior, bypass safety filters, or extract system prompts were detected in the instructions or examples.
Audit Metadata