ag2-overview
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the framework and its provider-specific extras (e.g.,
ag2[openai],ag2[anthropic]) using standard package managers like pip. - [COMMAND_EXECUTION]: Includes a benign shell command (
python -c "...") designed for users to sanity-check their Python environment and verify the installed version of the package. - [CREDENTIALS_UNSAFE]: Mentions the use of environment variables for API keys (e.g.,
OPENAI_API_KEY,ANTHROPIC_API_KEY) and correctly identifies the use of.envfiles andpython-dotenvas a common and safe pattern for local configuration.
Audit Metadata