service-quota-check
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [Command Execution]: The skill instructs the agent to execute multiple AWS CLI commands to interact with Service Quotas, CloudWatch, and various resource services (EC2, VPC, RDS, Lambda, etc.). These commands include both read operations (e.g.,
list-service-quotas,describe-instances) and write operations (e.g.,request-service-quota-increase,create-support-case). While these are necessary for the skill's purpose, they represent a significant capability tier that requires appropriate IAM permission scoping. - [Indirect Prompt Injection Surface]: The skill ingests data from external sources, specifically the output of AWS API calls (such as quota names, service names, and metric data) and user-supplied parameters. This data is then used to construct subsequent commands and logic.
- Ingestion points: Service codes, quota codes, and utilization metrics retrieved via AWS CLI in
SKILL.md. - Boundary markers: None explicitly defined to separate untrusted data from instructions.
- Capability inventory: Extensive command execution capabilities using the AWS CLI for service management and support case creation.
- Sanitization: No explicit sanitization or validation of the retrieved API data is mentioned before processing.
Audit Metadata