hugging-face-dataset-viewer
Warn
Audited by Snyk on Jul 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The required workflow calls Hugging Face Dataset Viewer endpoints like
/first-rows,/rows,/search,/filter, and/parquet, which at runtime return dataset content authored by third parties (outsider datasets) that the agent would ingest as readable JSON/text into the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata