doc-coauthoring

Warn

Audited by Snyk on Apr 28, 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's Stage 1 "素材处理" and the "如果需要补充信息" instructions explicitly require reading/analyzing user-provided reference materials and proactively searching the open internet for viewpoints/cases/data (public third‑party content), which the agent must interpret and incorporate into writing decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 28, 2026, 03:53 PM
Issues
1