huggingface-best

Warn

Audited by Snyk on Aug 15, 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 skill queries HuggingFace API endpoints at runtime for dataset lists, leaderboard entries, and model metadata, ingesting outsider-authored free text that appears in returned fields like dataset descriptions/metadata and model card/tags (“cardData”) into the LLM’s context for selection/filtering.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 15, 2026, 03:42 AM
Issues
1
Security Audit — snyk — huggingface-best