scheduler

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill’s cron examples include prompts like "搜索并总结今天最重要的 AI 新闻" (in the alma cron add "AI news digest" example), which clearly expect the agent to fetch and interpret open/public news content (untrusted third-party sources) as part of scheduled job execution.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 06:53 AM