azure-ai-contentsafety-java
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill utilizes official Azure SDK packages (
com.azure:azure-ai-contentsafetyandcom.azure:azure-identity) from a trusted organization (Microsoft/Azure). Use of these packages follows established security best practices for enterprise cloud services. - [SAFE]: The documentation identifies hardcoded credentials as an anti-pattern in the acceptance criteria and provides secure code examples using
System.getenv()andDefaultAzureCredential. This prevents accidental exposure of sensitive API keys. - [SAFE]: File access and network operations are limited to the skill's primary function of content moderation (e.g., reading local image files for analysis or providing a blob URL for remote analysis). There are no patterns suggesting unauthorized file access or data exfiltration.
- [SAFE]: The skill includes robust error handling patterns, specifically catching
HttpResponseException, which promotes secure and predictable application behavior during API failures. - [SAFE]: No malicious obfuscation, prompt injection, or remote code execution patterns were detected in the instructions or code snippets.
Audit Metadata