developing-aws
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill serves as a high-quality educational resource for AWS architecture.
- [EXTERNAL_DOWNLOADS]: The skill references downloads for established infrastructure tools such as eksctl, metrics-server, and argo-rollouts, as well as AWS-provided CloudFormation templates and manifests. All sources are official GitHub repositories or AWS-managed S3 buckets, which are recognized as trusted sources.
- [COMMAND_EXECUTION]: Includes standard CLI commands for AWS, kubectl, and CDK. These are used strictly for instructional purposes to demonstrate deployment and testing workflows.
- [PROMPT_INJECTION]: The skill provides patterns for building AI-integrated systems that handle untrusted data (Indirect Prompt Injection surface). It mitigates potential risks by documenting the use of XML delimiters in prompt templates and implementing Amazon Bedrock Guardrails for content filtering and PII masking, as seen in the GenAI and RAG reference files.
Audit Metadata