autoresearch-ml
Warn
Audited by Snyk on Sep 24, 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 workflow downloads training data shards and evaluation shards from HuggingFace (
huggingface.co/datasets/karpathy/climbmix-400b-shuffle), which contain outsider-authored text that is parsed and ingested during training.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata