azure-speech
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill is configured to fetch technical documentation from
learn.microsoft.com. This is an official domain for Microsoft documentation and is considered a well-known and trusted source. - [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for fetching external Markdown content at runtime using
fetch_webpageormicrosoft_docs_fetchtools. - Ingestion points: Content is retrieved from
learn.microsoft.combased on the Category Index inSKILL.md. - Boundary markers: The skill does not explicitly define delimiters for retrieved content.
- Capability inventory: The skill does not contain any file-write, command execution, or other high-privilege capabilities.
- Sanitization: No explicit sanitization is performed by the skill, relying on the agent's default processing of fetched documentation.
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access attempts were detected. The skill's behavior is consistent with its stated purpose as a developer reference tool.
Audit Metadata