skills/mukul975/anthropic-cybersecurity-skills/securing-azure-with-microsoft-defender/Gen Agent Trust Hub
securing-azure-with-microsoft-defender
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The Python script 'scripts/agent.py' executes system commands through 'subprocess.run' to interact with the Azure CLI (az). While it utilizes list-based arguments to mitigate shell injection, the commands incorporate user-controllable parameters such as file paths and lookback periods.
- [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes data from Azure APIs.
- Ingestion points: Data is ingested from Azure via 'az security' commands within 'scripts/agent.py'.
- Boundary markers: No explicit delimiters or instructions are used to isolate external data from the agent's control logic.
- Capability inventory: The script has the ability to execute CLI commands and write to the local filesystem via 'generate_posture_report'.
- Sanitization: External content returned by the Azure CLI is used directly in console output and JSON reports without prior sanitization or escaping.
Audit Metadata