azure-content-safety
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation from Microsoft's official
learn.microsoft.comdomain. This is a well-known, trusted service and is consistent with the skill's stated purpose of providing technical guidance. - [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for indirect prompt injection because it retrieves and processes content from external web pages.
- Ingestion points: Remote documentation URLs (e.g.,
https://learn.microsoft.com/en-us/azure/ai-services/content-safety/...) listed throughoutSKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present for the fetched content.
- Capability inventory: The skill uses network retrieval tools (
mcp_microsoftdocs:microsoft_docs_fetch,fetch_webpage). It lacks higher-risk capabilities such as file system writes, subprocess execution, or sensitive data access. - Sanitization: The skill does not specify any sanitization or validation logic for the fetched markdown content.
Audit Metadata