Unverified50% confidenceBenchmarkExact time
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
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/24/2026
First Seen
Valid until: 10/22/2026
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% similarUnverifiedAccount permission logic generated by Vibe Coding is often the most prone to security vulnerabilities, as AI may generate permission-checking code that appears correct but can actually be bypassed75% similarUnverifiedSecurity vulnerability rates in AI-generated code are 2.74x higher than in human-written code74% similarUnverifiedCybersecurity capability can be seen as a byproduct of strong coding ability; models that can understand complex code logic and locate bugs inherently have the potential to discover security vulnerabilities.73% similarUnverifiedNormal Security披露的GitLost研究指出，当AI编程代理能访问多个仓库时，一条公开issue可能成为数据泄露入口73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/604683API
curl https://kongchang.com/api/v1/knowledge/claims/604683MCP
get_claim(id=604683)