investment-research-prompts
Warn
Audited by Snyk on Mar 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md Freshness Rule and Suggested Workflow (step 6) explicitly require the agent to "先取得最新資料與來源/先查證再回答" for market data (e.g., 最新股價, 估值倍數, 分析師共識), which forces fetching and consuming external public third‑party sources that could carry untrusted/user-generated content and thereby influence analysis or tool actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata