soia-cwork-feishu-cli
Warn
Audited by Snyk on Jul 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). 该技能的运行时流程会通过
lark-cli wiki/drive/docs +fetch/+inspect读取飞书侧的 Wiki/文档正文与元数据(属于外部系统返回的自由文本/内容),并将其作为“文档摘要/分析输入”进入 agent 的 LLM 上下文;因此存在外部内容驱动的间接提示注入风险。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata