Unverified50% confidenceBenchmarkExact time
Among the AI agent platforms tested, the rate of private data leaking across users reached as high as 71%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
UnverifiedUsing local proxy tools to take over AI IDE traffic carries security risks including plaintext storage and leakage of API keys, code data privacy being logged and uploaded, and man-in-the-middle attacks72% 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71% similarUnverifiedBrain activity is regarded as the most private personal data, and the maturation of AI decoding capabilities will give rise to serious privacy and ethical issues.70% similarUnverifiedMany AI models have scraped massive amounts of web data without explicit authorization, raising legal and ethical issues related to copyright and privacy.70% similarVerifiedProduction data often contains user privacy information and commercially sensitive data, and directly exposing it to AI systems carries compliance risks69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/976533API
curl https://kongchang.com/api/v1/knowledge/claims/976533MCP
get_claim(id=976533)