bigml
Warn
Audited by Snyk on Apr 26, 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's SKILL.md explicitly lists a "Create Source from URL" action that ingests remote URLs (CSV/JSON), so the agent will fetch and interpret arbitrary third-party content which can materially influence dataset/model creation and subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata