awsflow-cloudformation
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from AWS CloudFormation that could potentially contain malicious instructions.
- Ingestion points: The skill retrieves templates and event logs via commands like GetTemplate and DescribeStackEvents.
- Boundary markers: No delimiters or specific instructions are provided to mitigate the processing of embedded instructions in external data.
- Capability inventory: The tool possesses administrative capabilities such as CreateStack and DeleteStack.
- Sanitization: The instructions do not specify validation or sanitization for retrieved infrastructure data.
Audit Metadata