marx-perspective
Warn
Audited by Snyk on Apr 24, 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). Yes — SKILL.md's Agentic Protocol Step 2 explicitly requires using web search/fetch_webpage to obtain real-world information ("必须使用工具(web search、fetch_webpage…)获取真实信息,不可跳过"), and the examples/references (examples/modern-cases.md, references/dialectical-examples.md) show using fetch_webpage to pull public statistics and reports which the agent must read and use to drive its analysis and decisions, exposing it to untrusted third‑party web content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata