Skills
skills/orcaqubits/agentic-commerce-claude-plugins/a2a-agent-card/Gen Agent Trust Hub

a2a-agent-card

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides purely instructional content for building discovery documents based on the A2A protocol.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to use WebFetch to retrieve documentation from https://a2a-protocol.org/latest/specification/. This is used for information gathering regarding the Agent Card schema and does not involve executing remote code or downloading untrusted binaries.
  • [PROMPT_INJECTION]: No evidence of prompt injection, jailbreak attempts, or instructions to override safety guidelines were found.
  • [DATA_EXFILTRATION]: The skill does not access sensitive local file paths (such as SSH keys or credentials) or perform unauthorized network exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 07:31 AM
Security Audit — agent-trust-hub — a2a-agent-card