azure-data-science-vm
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation from learn.microsoft.com using tools provided by the author. This is a standard and expected functionality for a technical reference skill.- [PROMPT_INJECTION]: The skill processes external data from learn.microsoft.com (ingestion point in SKILL.md). While no boundary markers or sanitization are explicitly defined, the lack of dangerous capabilities like file writing or code execution in the skill's own code (capability inventory) minimizes the risk of indirect prompt injection. No direct injection patterns were found.- [REMOTE_CODE_EXECUTION]: No unauthorized remote code execution patterns were detected. The referenced GitHub repository belongs to the trusted author organization.
Audit Metadata