azure-ai-contentsafety-py
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the official
azure-ai-contentsafetylibrary from Microsoft, a well-known and trusted vendor. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to process and analyze untrusted text and image data. * Ingestion points: Untrusted data enters the agent context via the
textparameter inAnalyzeTextOptionsand theimageparameter (via content or blob_url) inAnalyzeImageOptionsinSKILL.md. * Boundary markers: No explicit boundary markers or delimiters are defined in the provided code snippets to separate untrusted data from instructions. * Capability inventory: The skill utilizes theContentSafetyClientandBlocklistClientto perform network operations against Azure Cognitive Services endpoints. * Sanitization: The skill performs moderation and classification of external content using Azure's AI Content Safety service.
Audit Metadata