microsoft-agent-framework
Pass
Audited by Gen Agent Trust Hub on May 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely informational, providing high-level steps for role separation, workflow control, and governance in agent systems.
- [EXTERNAL_DOWNLOADS]: The skill includes a reference to the official Microsoft GitHub repository for the agent framework, which is a well-known and trusted source.
- [PROMPT_INJECTION]: No instructions were found that attempt to bypass safety guidelines, override system prompts, or extract internal configuration.
- [COMMAND_EXECUTION]: Although the skill is configured with access to tools like Bash, it does not include any automated scripts or command-line instructions that could be executed maliciously.
Audit Metadata