Unverified50% confidenceTradeoffExact time
Under the old model, AI Agents accessing cross-application resources must hold credentials for multiple applications separately, resulting in blurred permission boundaries, difficult auditing, and a single-point compromise affecting the entire chain.
1
Sources
50%
Confidence
Long-term
Relevance
9/7/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedNormal 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70% similarUnverifiedAttackers can exploit stolen AI service account credentials to call API interfaces for computing power theft, and such behavior has frequently appeared in terms-of-service violation reports on platforms such as OpenAI and Anthropic.68% similarUnverifiedUsing 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 attacks67% similarUnverified在具备工具调用能力的 Agentic 系统中，一次成功的提示注入可能导致数据泄露、恶意代码执行甚至供应链攻击66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/873108API
curl https://kongchang.com/api/v1/knowledge/claims/873108MCP
get_claim(id=873108)