huggingface-trackio
Warn
Audited by Snyk on Aug 26, 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). In the “Autonomous ML Experiment Workflow,” the agent polls
trackio list alerts ... --json(and then inspects snapshots/metrics) which include outsider-authored free text from alert fields (title/text) that a user can submit viatrackio.alert()during training.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata