azure-resource-visualizer

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill executes az CLI commands to perform its core function of Azure resource discovery and analysis. This is a legitimate but notable capability.\n- [EXTERNAL_DOWNLOADS] (LOW): The documentation mentions installing the resource-graph Azure CLI extension. Per [TRUST-SCOPE-RULE], this is a low-risk finding because the source (Microsoft) is a trusted organization.\n- [PROMPT_INJECTION] (LOW): The skill is vulnerable to Indirect Prompt Injection (Category 8) due to its processing of untrusted metadata from the cloud environment.\n
  • Ingestion points: Resource names, tags, and properties fetched from Azure via CLI tools (referenced in SKILL.md and azure-resource-graph.md).\n
  • Boundary markers: No specific delimiters or safety warnings are used when interpolating Azure resource data into prompts or diagrams.\n
  • Capability inventory: Terminal access for az commands and file writing capabilities to generate markdown documentation.\n
  • Sanitization: The skill does not implement sanitization for strings retrieved from Azure before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 03:34 AM