kaggle
Warn
Audited by Snyk on May 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests public, user-generated Kaggle content — e.g., the comp-report module scrapes competition pages and writeups via Playwright/list_competition_pages (modules/comp-report/README.md and modules/kllm/references/competition-overview.md) and the kllm/hackathon module fetches hackathon writeups via MCP endpoints like list_hackathon_write_ups/get_writeup (modules/kllm/hackathon/README.md and hackathon-endpoints.md) and those results are read and used by the agent to build reports and drive actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata