job-article
Warn
Audited by Snyk on May 14, 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 — the workflow's Step 2 "搜集资料" explicitly requires using联网搜索 (e.g., "web_search") to fetch current open-web sources (companies, salary data,面经), and those third‑party results are required inputs that the agent must read and use to shape article content and decisions (e.g., labeling sources as "网传" vs "已确认").
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata