travel-planner

Warn

Audited by Snyk on Mar 6, 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 instructs in "执行方式" and "输出规范" to use search-class Skills (e.g., jina-reader or web_search) to fetch latest public web information such as weather and prices, which the agent would read and use to influence itineraries and budgets, exposing it to untrusted third-party content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 04:20 PM