Skills
Navigate
skills/orcaqubits/agentic-commerce-skills-plugins/a2a-testing/Gen Agent Trust Hub

a2a-testing

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest data from external websites and search results to perform its tasks. \n
  • Ingestion points: WebFetch of https://a2a-protocol.org/latest/specification/ and WebSearch results for the a2aproject GitHub organization.\n
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present when processing this external data.\n
  • Capability inventory: The skill has access to Bash, Write, Edit, and WebFetch tools, providing a surface for action if instructions are injected.\n
  • Sanitization: There are no instructions for validating or sanitizing the content retrieved from external sources.\n- [EXTERNAL_DOWNLOADS]: The skill provides instructions to fetch protocol specifications and SDK documentation from a2a-protocol.org and search for resources within the a2aproject GitHub repositories.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 06:32 PM