a2a-server
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch documentation and search for reference implementations from external sources such as a2a-protocol.org and GitHub. This external data is used to inform the implementation of the server logic.
- Ingestion points: Instructions in
SKILL.mddirect the agent to useWebFetchandWebSearchto retrieve protocol specifications and code samples. - Boundary markers: The skill does not provide explicit boundary markers or instructions to ignore potential commands embedded in the fetched content.
- Capability inventory: The skill uses
Write,Edit, andBashtools to implement the server according to the retrieved documentation. - Sanitization: There are no prescribed steps for sanitizing or validating the content of the external documentation.
- Context: This behavior is inherent to the primary purpose of the skill, which is to implement a specific protocol from its documentation, and no malicious intent was observed.
Audit Metadata