microsoft-agent-framework
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: A potential prompt injection was detected in
references/official-docs/integrations/by-component/ui/ag-ui/security-considerations.md. Upon manual review, the content is part of a documentation section describing message list injection as a threat vector for educational purposes. It is not an active attempt to override system instructions. - [SAFE]: The skill is an extensive documentation resource for building .NET AI agents. It follows security best practices by documenting trust boundaries, recommending restricted permissions, and advising the use of Managed Identity over developer credentials for production deployments. No indicators of data exfiltration, malicious script execution, or persistence were identified.
Audit Metadata