analiza aiqbench
Hackers are exploiting compromised session keys on Anthropic's platform to mint unauthorized OAuth tokens and drain subscription allowances for AI agents. This security breach highlights critical vulnerabilities in how third-party integrations and session management protect user resources in production AI workflows. The incident underscores the urgent need for robust authentication protocols as reliance on autonomous AI agents grows within business operations.
Hackers are stealing Claude tokens from subscribers
Last month, a Claude user noticed his account was consuming tokens even though he wasn't working. Anthropic has since warned users about hackers.
On August 4, Grant de Swardt, an independent AI consultant in East Sussex, UK, noticed something strange going on with his Claude Max 20x account. He hadn’t been working that day, yet his token usage was climbing. The next day, he disabled everything he had attached to Claude and did not work with it. Token consumption again increased. “In the clearest controlled interval, it increased from 45% to 55% while I performed no work, scheduled Cowork tasks were paused or…
Extras afișat conform termenilor RSS ai publicației · 80 cuvinte · textul integral și figurile sunt pe site-ul publicației
Subiecte conexe
Links #5: 2026/07
LessWrong · 31 iul. 2026
[AINews] not much happened today
Latent Space · 3 oct. 2026
Hackers Target Claude, Cursor and Codex AI Agents to Steal Tokens and Prompt Histories
Cybersecurity News · 9 sept. 2026
OpenRouter: from Seed to Stripe — with OpenRouter’s Alex Atallah & AMP’s Anjney Midha
Latent Space · 25 sept. 2026