azure-machine-learning

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were detected.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill retrieves documentation from learn.microsoft.com. This is a well-known service, and the operations do not involve access to sensitive local files, environment variables, or hardcoded credentials.
  • [INDIRECT_PROMPT_INJECTION]: While the skill ingests external documentation, it incorporates strong defensive guidelines. It explicitly instructs the agent to treat fetched text as untrusted reference data and to ignore any embedded instructions, tool requests, or unrelated links.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 05:50 PM
Security Audit — agent-trust-hub — azure-machine-learning