ai-ecommerce-expert-batch-video-variations
Warn
Audited by Snyk on Aug 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: 0.30). 该技能在运行时通过 scripts/imiva_mcp.py 调用 IMIVA MCP 工具(如 create_video_generation_task),把用户在 prompt/args 中提供的自由文本作为 LLM 可读输入直接提交给第三方生成任务,但工作流未显示在生成前对文本来源/可信度进行筛选。
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill invokes npx to fetch and execute the remote npm package "@infimind/ecom-content-cli@latest" at runtime (e.g., via npx -y @infimind/ecom-content-cli@latest), which downloads and runs remote code as a required dependency.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). 该 Skill 明确调用并暴露与“积分/计费”相关的 MCP 接口(如 get_user_credits、create_video_generation_task),并包含 dryRun 与正式创建付费任务、设置 maxCredits(整单上限)、以及“积分不足/在平台充值”说明。也就是 Skill 可以在 MCP 上发起会消耗平台积分/计费的任务并设置消费上限,属于能够直接触发金钱/积分支出的操作,因此判定为具备直接财务执行能力。
Issues (3)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata