AGENT LAB: SKILLS

kaggle

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The comp-report module explicitly uses Playwright to navigate and scrape public Kaggle pages (e.g., https://www.kaggle.com/competitions/{slug}/overview, /writeups, leaderboards and top notebooks), which are user-generated, untrusted third‑party content that the agent reads and interprets as part of its reporting workflow, creating a path for indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:02 AM