deepagents
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill's documentation or provided code examples.
- [EXTERNAL_DOWNLOADS]: The documentation includes instructions to install the deepagents, tavily-python, and deepagents-cli packages via standard package managers. These are legitimate dependencies for the framework.
- [COMMAND_EXECUTION]: The framework includes a FilesystemBackend that provides agents with tools for local filesystem interaction. These capabilities are presented as intended features for building coding agents and include options for sandboxed operations.
- [CREDENTIALS_UNSAFE]: Examples demonstrate how to configure API keys using environment variables and standard placeholders, adhering to secure development practices.
Audit Metadata