According to Beating, Vercel has open-sourced deepsec, an AI-driven security testing framework that enables developers to scan large codebases locally without exposing source code to external cloud services. The framework employs a multi-stage verification workflow: after initial regex filtering, an AI Agent traces data flows and generates reports; a second Agent then performs validation to eliminate false positives, keeping error rates between 10% and 20%. For large repositories requiring days of single-machine processing, deepsec distributes scanning tasks across Vercel Sandboxes, supporting concurrent execution of over 1,000 sandboxes. The system also offers plugin mechanisms allowing Agents to write custom regex matchers for project-specific authentication logic and data layers.
Disclaimer: The information on this page may come from third parties and does not represent the views or opinions of Gate. The content displayed on this page is for reference only and does not constitute any financial, investment, or legal advice. Gate does not guarantee the accuracy or completeness of the information and shall not be liable for any losses arising from the use of this information. Virtual asset investments carry high risks and are subject to significant price volatility. You may lose all of your invested principal. Please fully understand the relevant risks and make prudent decisions based on your own financial situation and risk tolerance. For details, please refer to
Disclaimer.
Related Articles
TT Chain Integrates AegisAI Security System for RWA Protection on May 11
According to TT Chain's announcement on May 11, the Layer-2 blockchain network integrated AegisAI's AI-driven security infrastructure into its real-world asset ecosystem. The collaboration enhances protection for tokenized asset transactions and cross-chain operations through advanced threat
GateNews9h ago
JD.com Upgrades Self-Developed AI Agent, User Growth Exceeds 300% in Q1
According to CEO Xu Ran at JD.com's earnings call on May 12, the company is comprehensively upgrading its self-developed AI agent to more precisely identify, activate, and match user needs. JD.com's AI assistant Jingdong Jingyan saw user usage increase over 300% year-over-year in the first
GateNews9h ago
The Graph Launches x402 Payment Feature Supporting USDC Per-Request On-Chain Data Access on May 12
According to The Graph's official announcement on May 12, Graph Gateway now supports x402 Payments, enabling developers and AI Agents to access on-chain data via USDC per-request payments without requiring API keys, accounts, or dashboards. Users receive an HTTP 402 response containing price
GateNews10h ago
SAP Invests in n8n, Doubling Workflow Automation Platform's Valuation to $5.2B
According to Bloomberg, SAP invested in n8n on Tuesday, doubling the workflow automation platform's valuation to $5.2 billion. The German software giant also signed a multi-year partnership agreement with n8n to integrate the platform's tools into SAP's Joule Studio AI agent-building platform,
GateNews11h ago
Artificial Analysis Releases Coding Agent Benchmark; Zhipu GLM-5.1 Ranks First Among Open-Source Models
Artificial Analysis released a new Coding Agent Index today to evaluate how AI models perform when combined with agent frameworks across key benchmarks including SWE-Bench-Pro-Hard-AA, Terminal-Bench v2, and SWE-Atlas-QnA. Zhipu GLM-5.1 ranked first among open-source models in the evaluation,
GateNews11h ago
DAPPOS Launches xBubble, Universal AI Agent with 10+ Core Features for Non-Technical Users
According to ChainCatcher, DAPPOS officially launched xBubble, a universal AI agent product designed for non-technical users. The product automatically recommends specialized agents to complete tasks with minimal prompts and fewer debugging iterations. xBubble provides 10+ core capabilities
GateNews16h ago
