azure-active-directory-b2c

Pass

Audited by Gen Agent Trust Hub on May 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is configured to fetch remote documentation from learn.microsoft.com. These operations are transparently documented and target a well-known, official service owned by the vendor.
  • [PROMPT_INJECTION]: Contains standard instructional guidelines for the agent to navigate the document index and verify metadata timestamps. No attempts to override safety protocols or extract system prompts were detected.
  • [COMMAND_EXECUTION]: No shell commands or direct executable scripts are present. The skill relies on pre-defined platform tools for documentation retrieval.
  • [DATA_EXFILTRATION]: No sensitive file access or unauthorized network transmissions were found. Network activity is limited to retrieving public documentation with telemetry query parameters (from=learn-agent-skill).
  • [SAFE]: The skill adheres to best practices for documentation indices, utilizing trusted sources and providing clear instructions for agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
May 29, 2026, 07:09 AM
Security Audit — agent-trust-hub — azure-active-directory-b2c