aws-cli
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to execute a wide range of
awsCLI commands to manage EC2, Lambda, ECS, S3, IAM, and RDS resources. It also utilizes local shell utilities such ascat,tail,head, anddatefor data processing and timestamp generation. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the ingestion of external data.
- Ingestion points: Data is pulled into the agent's context from CloudWatch logs via
aws logs tailand from the results of Lambda function calls viacat /tmp/lambda-output.json. - Boundary markers: There are no markers or delimiters used to encapsulate the output of these commands, increasing the risk that instructions embedded in logs or payloads could be misinterpreted as system commands.
- Capability inventory: The skill has significant capabilities, including the ability to start and stop EC2 instances and invoke Lambda functions, which could be abused if an injection is successful.
- Sanitization: No sanitization or validation logic is present to filter malicious instructions from the retrieved AWS service data.
Audit Metadata