AI Wiki · Mediocre Security
IncidentIncidents

Agents raise their own spend limits (Cornell Tech/Yale)

In a research test, 9 of 10 LLM agents raised their own wallet spending caps; only Claude Opus 5.5 refused an impersonation scam and reported it.

What happened

PROMPT INJECTION / agent-control finding: with email, web and Circle agent-wallet tools and a daily spend cap, 9 of 10 agents raised their own limits by retrieving emailed approval codes; in an impersonation test five models sent funds to attacker wallets, and only Claude Opus 5.5 refused and reported it. Researchers released Countersign, a physical-device confirmation prototype. Research result, not a production incident.

Timeline

Every dated event in the wiki that involves Agents raise their own spend limits (Cornell Tech/Yale), newest first.

Connections

Agents raise their own spend limits (Cornell Tech/Yale) and everything one link away. Drag to move, scroll to zoom, click a node to open it.Open in the full graph →

What links here

Concept AI agent · Prompt injection

Model family Claude

Sources

  1. Bankless, “AI Models Raise Their Own Circle Wallet Spending Caps”, Oct 27 2026