feynman-perspective

Warn

Audited by Snyk on Apr 9, 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). SKILL.md's required Step 2 explicitly mandates using tools ("必须使用工具(WebSearch等)获取真实信息,不可跳过") and the skill's references list public web sources (Caltech, Wikipedia, news sites, etc.), so the agent will fetch and interpret untrusted third‑party content that can materially influence its answers and actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 9, 2026, 08:52 AM
Issues
1