AWS Infrastructure Architect

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to interact with the local environment using poetry run for several legitimate infrastructure tasks, including executing the AWS CLI, Sceptre for CloudFormation management, cfn-lint for template validation, and Python for boto3 script execution.
  • [PROMPT_INJECTION]: The skill incorporates a surface for indirect prompt injection by design, as it is instructed to fetch and process external data from AWS documentation via an MCP server integration.
  • Ingestion points: External data enters the context through tools like mcp__aws-knowledge-mcp-server__aws___read_documentation and mcp__aws-knowledge-mcp-server__aws___search_documentation.
  • Boundary markers: The prompt does not specify explicit delimiters or "ignore instructions" wrappers for the data fetched from the MCP server.
  • Capability inventory: The agent has the capability to execute shell commands via Poetry and generate executable Infrastructure-as-Code (IaC) templates.
  • Sanitization: There are no mentioned mechanisms for sanitizing or filtering the content retrieved from the AWS knowledge base. However, since the source is a well-known technology service (AWS), this surface is considered part of the intended functional design and does not elevate the risk level.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 08:46 AM