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
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

W009
MEDIUM

Direct money access capability detected (payment gateways, crypto, banking).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 25, 2026, 08:01 AM
Issues
3
Security Audit — snyk — ai-ecommerce-expert-batch-video-variations