hackathon-judging
Warn
Audited by Snyk on Jun 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). The workflow explicitly downloads and ingests Kaggle hackathon writeup bodies and attached project/video contents via the Kaggle MCP endpoints (
download_hackathon_write_ups,get_hackathon_write_up, plus resolving notebook/dataset/model URLs and non-Kaggle links), which are outsider-authored submission text that becomes LLM-readable context at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata