aws-agentic-ai

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of high-quality technical documentation and legitimate shell scripts for AWS infrastructure management. No malicious patterns or security risks were identified.
  • [COMMAND_EXECUTION]: The repository includes deployment and validation scripts (deploy-template.sh, validate-deployment.sh) that use standard AWS CLI and AWS CDK commands. These scripts are intended for developer use and do not contain any hidden or suspicious execution patterns.
  • [EXTERNAL_DOWNLOADS]: The documentation references official and well-known software packages, such as the bedrock-agentcore Python library and the @apidevtools/swagger-cli Node.js package, both sourced from established public registries.
  • [CREDENTIALS_UNSAFE]: No hardcoded secrets or credentials were found. The skill consistently uses placeholders for sensitive values and emphasizes the importance of using the AgentCore Identity service and AWS Secrets Manager for secure credential storage.
  • [PROMPT_INJECTION]: The instructions in SKILL.md guide the agent to verify information using AWS MCP tools to ensure accuracy, without attempting to override safety guidelines or inject adversarial behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 05:03 AM
Security Audit — agent-trust-hub — aws-agentic-ai