wa-guardrails

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a code generation assistant and does not request high-privilege access, perform unauthorized network communication, or execute system commands.
  • [PROMPT_INJECTION]: The skill analyzes external inputs such as existing IaC files and previous review findings to generate recommendations. While this is an indirect prompt injection surface, it is a primary function of the skill and the output consists of human-readable code snippets designed for developer review before deployment.
  • Ingestion points: User-provided codebase files and prior assessment documents.
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: Generation of static snippets for AWS Config rules, SCPs, and IaC tools (CDK, CloudFormation, Terraform).
  • Sanitization: All recommendations are provided as text snippets for manual verification by the developer.
  • [EXTERNAL_DOWNLOADS]: The skill references official AWS documentation for technical framework guidance, which are trusted and well-known services.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 06:40 PM
Security Audit — agent-trust-hub — wa-guardrails