auto-benchmark
Warn
Audited by Snyk on Mar 18, 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 skill explicitly scrapes leaderboards (Phase 2.1) from URLs in competitive_registry.yaml and ingests open/public research and blogs (Phase 3.1: arXiv queries, competitor_blogs, citation tracking), and it uses that untrusted third-party content to drive hypothesis generation, experiments, and promotion decisions—so external content can materially influence agent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata