google-adk
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists of a large set of documentation and reference materials in Markdown format. It contains numerous code snippets and configuration examples intended for developer reference, but it does not include standalone executable scripts that run during the agent's operation.
- [SAFE]: All external resource references, including GitHub repositories and package installation commands (NPM, PyPI, Maven, Go modules), point to official Google organizations or well-known, reputable open-source projects and libraries.
- [SAFE]: The documentation features an extensive "Safety and Security for AI Agents" section, providing educational content on mitigating risks such as prompt injection and data exfiltration through the use of guardrails, sandboxing, and secure authentication patterns.
- [SAFE]: Authentication examples consistently use placeholders and recommend secure practices such as using secret managers or environment variables, avoiding the use of hardcoded sensitive credentials.
Audit Metadata