azure-ai-projects-dotnet
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates workflows that ingest untrusted data from external or local sources, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: Includes snippets for uploading local files and folders via
UploadFileandUploadFolder(Section 5), and a web search tool configured viaCreateWebSearchTool(Section 2). - Boundary markers: The code samples do not demonstrate the use of delimiters or specific instructions to the model to ignore instructions embedded within the ingested data.
- Capability inventory: The configured agents have access to powerful tools such as Web Search, Code Interpreter, and File Search, which could be abused if an injection is successful.
- Sanitization: No content validation, filtering, or escaping is shown in the provided examples for processing external data.
- [EXTERNAL_DOWNLOADS]: Installs official Microsoft Azure and Identity libraries from the public NuGet package registry.
- [COMMAND_EXECUTION]: Utilizes standard .NET CLI commands (
dotnet add package) to manage project dependencies.
Audit Metadata