azure-language-service
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation content from learn.microsoft.com and references the official MicrosoftDocs/mcp repository for tool installation. These resources are managed by the official vendor and are considered safe.
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it retrieves external web content from learn.microsoft.com to answer user queries. 1. Ingestion points: Remote content fetched via microsoft_docs_fetch or fetch_webpage in SKILL.md. 2. Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded instructions in the fetched documentation. 3. Capability inventory: The skill utilizes network fetching capabilities to retrieve documentation. 4. Sanitization: No specific sanitization or filtering of the external content is described. While the skill lacks explicit boundary markers, the risk is considered safe as it targets only official vendor documentation.
Audit Metadata