ag2-evaluation
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The installation instructions specify
pip install "ag2[openai,tracing]". This package is the official distribution for the AG2 framework, which is the primary dependency for this skill. - [COMMAND_EXECUTION]: The skill facilitates the execution of AI agent tasks through the
run_agentfunction and performs scoring using local Python logic. These operations are restricted to the local execution environment for the purpose of performance benchmarking. - [SAFE]: Analysis of the skill instructions and code snippets revealed no signs of malicious activity, such as credential harvesting, data exfiltration to untrusted domains, or code obfuscation. File system access for storing and loading runs (
store_dir,load_run) is limited to user-defined local directories.
Audit Metadata