product-spec-builder
Warn
Audited by Snyk on Jun 25, 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“优秀案例分析”中要求加载并分析外部网页内容(http://bananaslides.online/),属于运行时抓取/读取的公共网页自由文本,可能被注入到 LLM 上下文。
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.70). The skill explicitly instructs fetching and using content from http://bananaslides.online/ at runtime to "分析优秀案例,学习其产品设计思路和 AI 能力使用方式", so runtime-fetched content could be injected into the agent's context and directly influence prompts/outputs (URL: http://bananaslides.online/).
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata