sns
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides templates for publishing messages that may contain untrusted data from external sources.
- Ingestion points: Message bodies and attributes in
sns.publishcalls acrossSKILL.mdandnotification-patterns.md. - Boundary markers: The examples do not include explicit boundary markers or instructions to ignore embedded commands within the message payloads.
- Capability inventory: Includes network operations via
aws snsCLI andboto3to communicate with AWS SNS services. - Sanitization: The provided code examples show simple JSON serialization but do not include explicit validation or sanitization of input data before publishing.
Audit Metadata