a2a-authentication
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation from "a2a-protocol.org" and performs searches on GitHub for project-specific implementation examples.- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from external documentation sites and search results, which could be manipulated to contain malicious instructions targeting the agent context.
- Ingestion points: SKILL.md (fetches from "a2a-protocol.org" and GitHub search results).
- Boundary markers: Absent; the instructions do not include delimiters or specific warnings to ignore instructions found within the fetched content.
- Capability inventory: The skill is configured with access to "Write", "Edit", and "Bash" tools, allowing it to modify files or execute system commands based on processing results.
- Sanitization: Absent; there is no validation or filtering specified for the external content before it is processed by the agent.
Audit Metadata