infra-platform-aws-sdk
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for ingesting data from external sources such as S3 buckets, SQS queues, and SNS topics. This data is often parsed and used in downstream logic like Lambda invocations or database updates without explicit sanitization.
- Ingestion points:
examples/core.md(S3 object body viatransformToString),examples/messaging.md(SQSmessage.Body),examples/advanced.md(Lambdaresponse.Payload). - Boundary markers: Examples do not include prompt-level delimiters or instructions to ignore embedded commands in the fetched data.
- Capability inventory: Demonstrates remote service invocation (
InvokeCommand), file system access (node:fs), and extensive network operations. - Sanitization: Input validation logic is absent before data is used in downstream operations.
Audit Metadata