geopolitical-driver

Warn

Audited by Snyk on Feb 25, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to perform web searches and ingest public news sources (see "第二步:分层检索" and the "财联社搜索关键词模板"/信源标准 listing Reuters, Bloomberg, cailianpress, BBC, etc.), so the skill clearly fetches and reads open third‑party web content that can directly influence its trading/analysis decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 25, 2026, 03:26 AM