iac-security
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, untrusted IaC templates (Terraform, CloudFormation, Bicep, Pulumi) which serves as an attack surface for instructions embedded in code comments or string literals.
- Ingestion points: The skill uses Glob and Read tools to access local project files.
- Boundary markers: The skill contains a dedicated Prompt Injection Safety Notice section that explicitly instructs the agent to treat all template content as data and to ignore directives like # checkov:skip or # tfsec:ignore when performing the assessment.
- Capability inventory: The skill's execution environment is restricted to Read, Grep, and Glob, preventing any malicious instructions in analyzed files from triggering code execution or network operations.
- Sanitization: The instructions provide clear guidance on distinguishing between variable references and hardcoded secrets, reducing the risk of being misled by deceptive content.
Audit Metadata