a2a-protocol
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides comprehensive documentation and references for the A2A (Agent-to-Agent) protocol. Analysis of SKILL.md and its associated reference files (agent-card.md, protocol-bindings.md, task-states.md) reveals no malicious patterns.
- [COMMAND_EXECUTION]: The skill contains a standard companion check command to help users install recommended skills. This uses a
lscommand to check for existing skill directories and suggests annpxcommand for installation, which is standard practice for this platform and categorized as safe. - [DATA_EXFILTRATION]: There is no evidence of unauthorized data access or network transmission. All network-related examples (e.g., curl commands to fetch agent cards or JSON-RPC requests) are educational and target example/placeholder domains.
- [PROMPT_INJECTION]: No instructions were found that attempt to bypass safety filters or override the agent's core instructions. The instructions are focused on guiding the agent to correctly implement and explain the A2A protocol.
- [REMOTE_CODE_EXECUTION]: The skill does not download or execute remote scripts. It strictly provides static protocol documentation and configuration examples.
Audit Metadata