azure-resource-lookup
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses "az graph query" and "az extension add" to manage and retrieve Azure resource metadata. These are standard operations for the intended functionality and utilize official Microsoft Azure CLI tools.
- [PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection because it retrieves and processes metadata (such as resource names and tags) that can be configured by external users. While no malicious activity was found, this ingestion of external data is a known vulnerability surface.
- Ingestion points: Resource properties, names, and tags retrieved via Azure Resource Graph queries in SKILL.md and references/azure-resource-graph.md.
- Boundary markers: The skill does not define specific delimiters or instructions to treat the query output as untrusted data.
- Capability inventory: The skill can execute Azure CLI commands to interact with the cloud environment.
- Sanitization: There is no explicit sanitization or escaping of the metadata retrieved from Azure before it is presented to the agent.
Audit Metadata