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:
partsarray 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