azure-ai-projects-java
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the
azure-ai-projectsMaven dependency. This is an official library provided by a well-known service, used for legitimate cloud project management. - [INDIRECT_PROMPT_INJECTION]: The skill provides interfaces for dataset management and index creation, which are potential vectors for indirect prompt injection.
- Ingestion points: Untrusted data enters the agent context through document uploads (
DatasetsClient) and search index updates (IndexesClient). - Boundary markers: No explicit delimiters or boundary markers for external data are provided in the code examples.
- Capability inventory: The skill allows for the management of connections, datasets, deployments, indexes, and evaluations within an Azure AI Foundry project.
- Sanitization: The provided instructions do not include specific sanitization or validation logic for the content being uploaded or indexed.
Audit Metadata