pentest-gemini-az
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Azure CLI (
az) to perform cloud management tasks. - Evidence: Executes
az restfor generic API requests andaz accountfor managing session context (SKILL.md). - [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection (Category 8).
- Ingestion points: Fetches resource data and configuration details from Azure Resource Manager and Microsoft Graph API responses (SKILL.md).
- Boundary markers: Does not define clear delimiters or specify that the agent should ignore instructions embedded within the retrieved cloud resource data.
- Capability inventory: Can perform high-impact management actions, including creating and deleting cloud resources via
az rest(SKILL.md). - Sanitization: No sanitization or validation of data retrieved from external cloud APIs is described before the agent processes the content.
Audit Metadata