academic-paper-mentor

Warn

Audited by Snyk on Feb 27, 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 requires Stage 2 "文献调研与 Gap 分析" and lists tools "web_search" and "web_fetch" in the 配套工具 section, indicating the agent will fetch and read public third‑party literature/URLs (open web content) and use that content to drive its analysis and next actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 11:37 PM