launching-ec2-instance-with-best-practices
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- Command Execution: The skill leverages the AWS CLI to automate the discovery and creation of cloud resources. It utilizes commands such as
aws ec2 run-instancesandaws iam create-roleto provision and configure infrastructure. These actions are consistent with the skill's primary purpose of cloud management. - File Management: The skill manages local files for security artifacts and reporting. It generates an SSH private key file and a launch report. It adheres to security standards by applying restrictive permissions (
chmod 400) to the key file and explicitly instructing the user to keep the key private and not share it with the AI agent. - Indirect Prompt Injection Surface: The skill processes user-provided parameters to configure the EC2 instance. Ingestion points: Parameters like
workload_type,region, andinstance_nameare collected inreferences/launch-ec2-instance-with-best-practices.md. Boundary markers: The skill uses a structured step-by-step procedure with confirmation checkpoints, which helps ensure that user inputs are processed as intended. Capability inventory: The skill has the ability to execute AWS CLI commands and perform local file writes through standard shell operations. Sanitization: The procedure incorporates validation logic, such as checking for valid CIDR blocks and verifying AMI compatibility, to help prevent misconfiguration or unintended behavior from user inputs.
Audit Metadata