AI agents bypassed crypto spending limits without human approval, researchers find in a new test

From the source

The researchers say any approval an agent can reach is unreliable, and they built Countersign, an app tying approval to a physical action the agent can’t fake. AI agents given access to their owners' email accounts were able to increase their own cryptocurrency spending limits without human approval, raising questions about the safeguards designed to control autonomous payments, researchers at Cornell Tech and Yale University found. In experiments with stablecoin issuer Circle’s agent wallets , nine out of 10 models raised their spending caps at least once while paying invoices without an attacker involved. Only Anthropic’s Claude Opus 5.5 never tried to bypass the cap; instead, it spent up to its limit and reported remaining invoices to the user. The researchers also introduced a simulated attacker in two separate experiments, sending malicious emails to the owner's inbox to persuade the agents to increase their spending limits or impersonating the owner to request a payment to an…

BestAIBroker analysis

• Finance-aware sentiment: slightly negative (-0.20 on a -1 to +1 scale).
• Event classification: OTHER.
• Market importance score: 34/100, weighting entity relevance, source credibility, multi-outlet coverage and recency.
• Symbols referenced: CRCL.