azure-data-science-vm
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 and installation guides from official Microsoft Learn domains (learn.microsoft.com) and the author's GitHub repository (github.com/MicrosoftDocs).
- [INDIRECT_PROMPT_INJECTION]: The skill processes external documentation content, creating a potential surface for indirect prompt injection if the source content were to be compromised.
- Ingestion points: Documentation URLs listed in SKILL.md are accessed via the
mcp_microsoftdocs:microsoft_docs_fetchandfetch_webpagetools. - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" wrappers for the fetched external content.
- Capability inventory: The skill allows the agent to retrieve and read remote markdown documentation, which is then used to inform responses.
- Sanitization: There are no explicit sanitization or validation steps described for the content retrieved from the external documentation URLs.
Audit Metadata