aws-ai-ml
Warn
Audited by Snyk on Nov 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The auto-labeling workflow reads a user-selected corpus (local, S3, or DataSet ARN) that the agent only previews through its first rows (
corpus/head.jsonl), and the labeling job reads the rest in place. That corpus is the customer's own data rather than an outsider-submitted queue or feed, so exposure requires the user to point at an outsider-authored source.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata