azure-video-indexer
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and fetches content from official Microsoft documentation at learn.microsoft.com. These are established, official resources for Azure services.
- [INDIRECT_PROMPT_INJECTION]: The skill utilizes external documentation as a data source, which introduces a potential surface for indirect prompt injection if those external pages were compromised.
- Ingestion points: Documentation content is retrieved using
mcp_microsoftdocs:microsoft_docs_fetchorWebFetchas directed inSKILL.md. - Boundary markers: The instructions do not provide explicit boundary markers or instructions to the agent to treat the fetched documentation as untrusted data.
- Capability inventory: The skill primarily provides information and does not include capabilities for sensitive file access, arbitrary command execution, or network exfiltration of user data.
- Sanitization: No explicit sanitization or validation of the fetched Markdown content is implemented.
Audit Metadata