aws-bestpractice-research
Fail
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: HIGHCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute
source <credential-file-path>in thereferences/audit-workflow.mdfile, where the path is provided by the user. This operation executes any shell script content within the specified file in the current shell environment. - [COMMAND_EXECUTION]: The workflow constructs numerous AWS CLI commands (e.g.,
aws elasticache describe-replication-groups --replication-group-id {REPL_GROUP_ID}) by directly interpolating user-controlled variables. This pattern is highly susceptible to command injection if the input strings contain shell metacharacters or additional commands. - [CREDENTIALS_UNSAFE]: The skill's primary workflow (Step 1 and Step 8.1) explicitly prompts users to provide high-privilege AWS credentials, including environment variables, profile names, and credential file paths.
- [COMMAND_EXECUTION]: The skill includes complex audit logic for multiple AWS services (RDS, MSK, DynamoDB, EKS) that relies on executing shell-based CLI operations with interpolated resource identifiers provided by the user.
Recommendations
- AI detected serious security threats
Audit Metadata