aws-solution-architect
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local Python scripts (
architecture_designer.py,serverless_stack.py,cost_optimizer.py) and standard industry tools like the AWS CLI, CDK, and Terraform to automate architecture design and infrastructure deployment tasks. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided JSON files containing architectural requirements and resource inventories.
- Ingestion points: External data enters the context via
requirements.json,current_setup.json, andinventory.jsonas specified in the workflow instructions inSKILL.md. - Boundary markers: Explicit delimiters or instructions to ignore potential prompts within the JSON input are not implemented in the provided scripts.
- Capability inventory: The skill possesses the capability to execute shell commands for script execution and infrastructure deployment using standard AWS and IaC tools.
- Sanitization: The ingestion logic in the Python scripts primarily uses the data for conditional mapping (Enums) and string interpolation in templates, limiting the execution surface for data-based attacks.
- [SAFE]: The skill promotes secure infrastructure patterns, including IAM least privilege, data encryption at rest using KMS, and network isolation using VPC endpoints. No hardcoded credentials, obfuscation, or suspicious network activities were identified.
Audit Metadata