a2a-multi-turn

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or safety bypasses were detected. The skill instructions are consistent with its stated purpose of implementing a protocol.
  • [EXTERNAL_DOWNLOADS]: The skill fetches protocol specifications and documentation from a2a-protocol.org and GitHub. These resources are appropriate for the task and are targeted neutrally.
  • [PROMPT_INJECTION]: Analysis of the data ingestion surface for potential indirect prompt injection. Ingestion points: a2a-protocol.org and GitHub (SKILL.md). Boundary markers: Absent. Capability inventory: Bash, Write, Edit, WebFetch tools (SKILL.md). Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 07:32 AM
Security Audit — agent-trust-hub — a2a-multi-turn