agent-usability-test
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional documentation and testing protocols. It does not contain any executable scripts, binary files, or automated commands that could pose a security risk to the host environment.
- [DATA_EXFILTRATION]: While the documentation mentions environment variables like 'SERPAPI_KEY' and discusses the use of 'HOME' and 'CWD' for environment isolation, these references are strictly for instructional purposes regarding standard benchmarking practices. No hardcoded credentials or automated data transmission mechanisms are present.
- [PROMPT_INJECTION]: The skill provides template prompts for testing purposes (e.g., 'Answer this: [GOAL]. Cite your source.'). These are standard instructional prompts used to evaluate agent discovery behavior and do not attempt to bypass safety filters or override agent constraints.
- [COMMAND_EXECUTION]: The documentation references external CLI tools such as 'copilot' and 'serpapi' to describe performance testing scenarios. These are not executed by the skill itself, and the vendor context (serpapi) aligns with the legitimate mention of these tools.
Audit Metadata