azure-ai-agents-persistent-java
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a standard workflow that ingests user input and processes it through an LLM, which represents a common interaction surface for indirect prompt injection.
- Ingestion points: User-provided strings are passed to the
messageClient.createMessagemethod inSKILL.md. - Boundary markers: The provided code snippets do not implement specific delimiters or instructions to isolate untrusted user content from the system prompt.
- Capability inventory: The skill uses subclients to manage agent administration, thread creation, and run execution within the Azure AI environment.
- Sanitization: No explicit input validation or escaping mechanisms are present in the documentation examples.
- [EXTERNAL_DOWNLOADS]: The skill references the
azure-ai-agents-persistentlibrary from Maven Central and provides links to the official Azure SDK for Java repository on GitHub. These references are to well-known and established resources from a recognized organization.
Audit Metadata