skills/nvidia-tao/tao-skill-bank/tao-finetune-cosmos-reason/Snyk

tao-finetune-cosmos-reason

Warn

Audited by Snyk on Oct 19, 2026

Risk Level: MEDIUM

Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

Third-party content exposure detected (medium risk: 0.30). The workflow reads training/evaluation dataset annotation JSON files provided by users or fetched from storage, which ingest outsider-authored free text into the dataset parser.

Issues (1)

W011

MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata

Risk Level

MEDIUM

Analyzed

Oct 19, 2026, 07:30 AM

Issues

1