azure-resource-visualizer

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Azure CLI (az) to retrieve infrastructure metadata, such as resource lists and network configurations. These commands are standard administrative tools used for read-only analysis.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes data retrieved from Azure (resource names, configurations, and tags) and interpolates it into Mermaid diagrams and markdown reports.
  • Ingestion points: Azure CLI output processed during resource analysis in SKILL.md.
  • Boundary markers: Absent; the skill does not define specific delimiters to isolate external Azure data from instructions.
  • Capability inventory: Azure CLI execution (az) and file-writing capabilities (creating .md files) are used in SKILL.md.
  • Sanitization: No specific sanitization or validation logic is mentioned for the data ingested from the Azure environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 12:20 AM
Security Audit — agent-trust-hub — azure-resource-visualizer