azure-resource-lookup

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • Command Execution: The skill generates and recommends the execution of az graph query commands. This allows the agent to interact directly with the Azure CLI to perform resource lookups as requested by the user.
  • External Downloads: The skill includes instructions to install the resource-graph extension for the Azure CLI. This is a standard official extension provided by the vendor to enable Resource Graph capabilities.
  • Dynamic Execution: The skill utilizes a command generation tool (extension_cli_generate) to dynamically construct shell commands based on user natural language prompts, which is a core component of its resource discovery logic.
  • Indirect Prompt Injection Surface: The skill's primary function involves retrieving and processing resource metadata from the Azure environment, which creates a surface where external data enters the agent's context.
  • Ingestion points: Resource metadata, including names, types, and tags, are ingested from the Azure environment via az graph query results as described in SKILL.md and references/azure-resource-graph.md.
  • Boundary markers: No explicit delimiters are specified in the instructions to separate resource data from agent instructions.
  • Capability inventory: The skill possesses the capability to generate and execute shell commands (az) across the Azure environment.
  • Sanitization: The skill does not describe specific sanitization or filtering steps for the retrieved resource metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 02:51 PM
Security Audit — agent-trust-hub — azure-resource-lookup