awsflow-sns
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides broad management capabilities for AWS SNS via the SNSTool in SKILL.md, including potentially destructive operations such as DeleteTopic, DeletePlatformApplication, and Unsubscribe. These commands allow an agent to modify cloud infrastructure state based on user-provided instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes user-provided data for message payloads and resource configurations in SKILL.md.
- Ingestion points: Data enters the context via parameters such as Message, Subject, TopicArn, phoneNumber, and Endpoint in the SNSTool.
- Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore embedded instructions within processed content.
- Capability inventory: The skill allows full lifecycle management of SNS resources and message publishing capabilities.
- Sanitization: No sanitization or validation logic is defined to pre-process inputs before they are passed to the AWS environment.
Audit Metadata