Unverified50% confidenceFactTime unknown
Security vulnerability rates in AI-generated code are 2.74x higher than in human-written code
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
Related Claims
UnverifiedAI 代码中最高频的两类安全问题是依赖安全与密钥泄露77% similarUnverified据GitHub的研究数据，AI生成的代码在安全漏洞密度上显著高于人工编写代码，主要集中在SQL注入、越权访问等漏洞类型74% similarUnverified信息安全中攻击面与代码量近似正相关，代码量精简的工具意味着更小的攻击面和更高可信度71% similarUnverifiedVibe Coding 生成的账号权限逻辑往往最容易出现安全漏洞，AI 可能生成看似正确但实际可被绕过的权限检查代码68% similarUnverifiedAI生成的Auth代码往往能覆盖基本功能流程，但在安全细节（如HttpOnly和Secure标志的Cookie、CSRF Token验证）方面容易出现疏漏68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/55420API
curl https://kongchang.com/api/v1/knowledge/claims/55420MCP
get_claim(id=55420)