HackerFeeds

CyberSecurity News

Critical x402 SDK Flaw Could Let Malicious APIs Drain AI Agents’ Token Balances

The Hacker News
· October 23, 2026

AI summary

A vulnerability in the x402 SDK could allow malicious APIs to drain the token balances of AI agents that use the SDK to pay for API calls. This is because the default client in the SDK did not set a spending limit, which could lead to AI agents signing payments for their full token balance if requested. However, this issue was addressed in releases made on August 18, which added a spending limit. The risk is specifically limited to AI agents that automatically sign payments and have apps that do not set spending limits. Affected AI agents could potentially have their token balances depleted by malicious APIs. The security firm V12 disclosed this information on October 22.

Read the full article at The Hacker Newsthehackernews.com/2026/10/critical-x402-sdk-flaw-could-let.html

This is an AI-generated brief aggregated by HackerFeeds for convenience and grounded in the source’s own summary; the related CVE, threat-group and country data is from HackerFeeds’ own indexes. The original article is the authoritative source — all rights belong to The Hacker News.