a2a-messages-parts

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch protocol schemas and specifications from https://a2a-protocol.org/latest/specification/ to inform the implementation of message parts.
  • [PROMPT_INJECTION]: The skill describes a surface for indirect prompt injection by defining how to process external message content. (1) Ingestion points: parts array in message structures (SKILL.md). (2) Boundary markers: Absent. (3) Capability inventory: Allowed tools include Bash, Write, and Edit. (4) Sanitization: Not specified in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 07:32 AM
Security Audit — agent-trust-hub — a2a-messages-parts