tgw-search
Fail
Audited by Snyk on Jun 29, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). 该 Skill 明确要求在对话中索要用户的 Perplexity/Tavily API Key 并将其写入本机配置(使用 --init-stdin 等操作),这意味着模型会接收并需在后续操作中处理/传递这些密钥,存在将秘密以明文出现在命令或输出中的外泄风险。
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). 运行时会通过 Tavily 的
include_answer: True获取其返回的answer(外部网页内容的综合文本/摘要,属于“公共网页内容 fetched at runtime”),并在tavily_markdown()/to_markdown()中作为可读文本拼入输出上下文供后续 LLM 读取。
Issues (2)
W007
HIGHInsecure credential handling detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata