tw-research-lit-review

Warn

Audited by Snyk on Apr 10, 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.md explicitly states it "支援 WebSearch 多資料庫搜尋" and lists public databases (e.g., Google Scholar, Web of Science, Scopus, CNKI) in the "資料庫搜尋清單" and then instructs the agent to collect those results and perform clustering/analysis ("收集到文獻清單後,執行聚類" and Steps 4–6), so the agent ingests and acts on untrusted third‑party web content that can influence its decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 10, 2026, 04:41 AM
Issues
1