create-infrastructure

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill contains no instructions designed to override the agent's safety protocols, bypass filters, or disregard previous instructions.
  • [DATA_EXFILTRATION]: No sensitive file access (such as .ssh or .aws config) or unauthorized network calls were detected. The skill correctly uses placeholders for sensitive identifiers like subscription IDs.
  • [REMOTE_CODE_EXECUTION]: There are no patterns involving the download and execution of remote scripts or the use of dynamic execution environments.
  • [COMMAND_EXECUTION]: No arbitrary command execution, privilege escalation attempts, or unauthorized shell operations were found.
  • [SAFE]: The skill follows best practices for infrastructure-as-code generation, utilizing standard templates and a dedicated MCP tool for its primary function.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 10:22 PM
Security Audit — agent-trust-hub — create-infrastructure