azure-ai-formrecognizer-java
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the official Microsoft Azure SDK dependency (com.azure:azure-ai-formrecognizer) via Maven configuration. This is a trusted resource from a well-known service provider.- [CREDENTIALS_UNSAFE]: The documentation correctly utilizes placeholders such as {key} and {endpoint} in its code examples. It explicitly guides users to manage secrets securely via environment variables or the DefaultAzureCredential class.- [DATA_EXFILTRATION]: The skill includes functionality for analyzing documents from URLs and local files. This behavior is consistent with the primary purpose of the Azure AI Document Intelligence SDK and does not involve unauthorized data transmission.- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it processes untrusted documents from external sources. However, as documentation for an official SDK, it does not introduce malicious logic.
- Ingestion points: Example code in SKILL.md processes local file paths and remote URLs.
- Boundary markers: Not explicitly defined in code samples.
- Capability inventory: Performs network operations to official Azure API endpoints.
- Sanitization: Responsibility is deferred to the SDK and the underlying Azure AI service.
Audit Metadata