aws-solution-architect
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external JSON files to drive architecture recommendations and IaC generation, which constitutes a potential attack surface.
- Ingestion points: The skill instructions and scripts (e.g.,
architecture_designer.py,cost_optimizer.py) specifically process data fromrequirements.jsonandinventory.jsonprovided via command-line arguments. - Boundary markers: There are no explicit delimiters or instructions to the agent to ignore or isolate instructions that might be embedded within the processed data files.
- Capability inventory: The skill possesses the capability to execute shell commands via Python scripts, the AWS CLI, and infrastructure-as-code deployment tools (CDK, Terraform).
- Sanitization: The Python implementation performs basic dictionary lookups and string replacements for resource naming but does not sanitize or validate the content of user-provided strings before they are interpolated into recommendations or generated code.
- [DYNAMIC_EXECUTION]: The
serverless_stack.pyscript dynamically generates executable infrastructure-as-code templates at runtime. - Evidence: The script uses Python f-strings to interpolate application names and requirements directly into CloudFormation YAML, CDK TypeScript, and Terraform HCL string blocks, which are then presented to the user for execution.
Audit Metadata