tw-stu-learning-portfolio

Warn

Audited by Snyk on Apr 23, 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 explicitly enables an automated WebSearch ("WebSearch(已啟用):搜尋最新課綱資料、教學素材、時事情境") as part of its MCP integration, meaning the agent will fetch and read open web content that could influence its outputs and actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 23, 2026, 02:35 AM
Issues
1