infrastructure-as-code

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill's primary workflow involves the agent executing CLI commands such as 'terraform plan', 'terraform apply', and 'pulumi up' to manage cloud infrastructure resources.
  • [EXTERNAL_DOWNLOADS]: The skill's examples reference external modules (e.g., 'terraform-aws-modules/vpc/aws') and providers which are downloaded from official registries during initialization.
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection via the processing of untrusted user input to generate executable code.
  • Ingestion points: The agent collects infrastructure requirements from the user in the initial workflow step (SKILL.md).
  • Boundary markers: No delimiters or instructions are provided to isolate user requirements from the code generation logic.
  • Capability inventory: The agent is authorized to execute complex cloud infrastructure commands and manage cloud resources across multiple providers.
  • Sanitization: There are no instructions for the agent to validate or sanitize user input before incorporating it into the generated IaC configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 09:02 PM
Security Audit — agent-trust-hub — infrastructure-as-code