team-builder

Warn

Audited by Snyk on Jul 4, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.65). 该技能在运行时会读取本地/全局目录中的外部 markdown 智能体文件内容(./agents/**/*.md、~/.claude/agents/**/*.md),其中这些文件可能由操作用户未编写的第三方提供,从而把其“角色提示/工作流程/交付物”等自由文本注入到 LLM(通过 prompt: "{agent file content}\n\nTask: {task description}")。

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 4, 2026, 07:07 PM
Issues
1