a2a-multi-turn
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily instructional, focusing on protocol state management and interaction patterns. No suspicious code or malicious commands are present in the provided instructions.
- [EXTERNAL_DOWNLOADS]: Fetches documentation from the official A2A protocol website and searches GitHub for relevant samples. These operations are intended to provide context for implementing the protocol and target appropriate technical resources.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it ingests external data through WebFetch and WebSearch while having the capability to modify files and execute shell commands. However, no malicious instructions targeting the agent's behavior were found. Ingestion points: WebFetch of documentation and WebSearch of GitHub in SKILL.md. Boundary markers: Absent. Capability inventory: Read, Write, Edit, Bash, Grep, Glob, WebSearch, WebFetch. Sanitization: Absent.
Audit Metadata