azure-load-balancer

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is a documentation resource for Azure Load Balancer and does not perform any malicious actions.
  • [EXTERNAL_DOWNLOADS]: The skill references numerous URLs from learn.microsoft.com to provide the agent with technical details.
  • All referenced URLs belong to the vendor's official documentation platform.
  • [PROMPT_INJECTION]: The skill incorporates external documentation content, which presents a surface for indirect prompt injection.
  • Ingestion points: Documentation is retrieved via mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage from the learn.microsoft.com domain.
  • Boundary markers: The skill lacks explicit instructions for the agent to use delimiters when processing retrieved external content.
  • Capability inventory: No dangerous capabilities, such as local file system access, command execution, or unauthorized network operations, are present in the skill.
  • Sanitization: No sanitization or filtering of the fetched content is implemented within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 08:30 AM