aws-solution-architect

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied application names to generate infrastructure templates (CloudFormation, Terraform, and CDK). The ServerlessStackGenerator class interpolates the app_name variable into these templates using f-strings. While it performs basic sanitization by converting to lowercase and replacing spaces with hyphens, it does not validate against special characters that could break the syntax of the generated YAML, HCL, or TypeScript code.
  • Ingestion points: Application name and requirement inputs processed by the ServerlessStackGenerator and ArchitectureDesigner classes.
  • Boundary markers: No specific boundary markers or 'ignore' instructions are used in the generated template strings.
  • Capability inventory: The skill identifies architecture patterns and generates text-based infrastructure code for the user to review and deploy; it lacks the capability to execute commands or make network requests.
  • Sanitization: Basic sanitization is applied to the application name (.lower().replace(' ', '-')).
  • [EXTERNAL_DOWNLOADS]: The documentation includes links to official AWS resources such as the Well-Architected Framework and the AWS Pricing Calculator, as well as official AWS sample repositories on GitHub. These references target well-known and trusted services.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 01:54 PM
Security Audit — agent-trust-hub — aws-solution-architect