azure-video-indexer
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch documentation from 'learn.microsoft.com' using specific tools like 'mcp_microsoftdocs:microsoft_docs_fetch'. These references target official documentation services associated with the vendor.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from remote URLs when fetching documentation.
- Ingestion points: Documentation is retrieved via 'mcp_microsoftdocs:microsoft_docs_fetch' or 'fetch_webpage' from remote web sources (SKILL.md).
- Boundary markers: None explicitly defined in the provided file to delimit external content from system instructions.
- Capability inventory: The skill uses tools to read files and fetch network content.
- Sanitization: No specific sanitization or validation of the fetched markdown content is described.
- [SAFE]: The skill references a repository on GitHub ('github.com/MicrosoftDocs') for an installation guide, which is a trusted organization. All external documentation links point to the official Microsoft Learn domain.
Audit Metadata