Critical x402 SDK Flaw Allows Malicious APIs to Drain AI Agent Token Balances

What happened

The x402 SDK’s default client did not enforce any spending limit, so a malicious API could request a payment that automatically signed off the full token balance of an AI agent. The SDK was patched on August 18 to add an optional limit, but older versions remain vulnerable.

Why it matters for trust and compliance

• The incident underscores the need for continuous AI‑governance controls that enforce spend limits and provide auditable evidence of third‑party API validation.
• Enforce spend‑limit controls and capture evidence for AI‑risk frameworks.
• Map the SDK‑spend‑limit control to the VCF control objective for AI governance, supporting multiple compliance regimes.

Who is affected

Recommended actions

1. Upgrade to the latest x402 SDK version that includes spending limits.
2. Configure explicit spend caps for all AI agents before deployment.
3. Implement runtime monitoring and alerts for abnormal token balance changes.
4. Document and map the spend‑limit control to your AI‑governance framework.