Registry/Agents/Claude
Agent Profile

Claude

Anthropic

Anthropic's AI assistant and agent, used via API, Claude.ai, and third-party integrations.

2
Cases
$18k
Damage
4.0/5
Severity
78
APM-0004·Claude·SEVERE·~$11kApr 24, 2026

Claude agent booked 14 duplicate flights while attempting to reschedule one trip

A travel assistant built on Claude was given access to a booking API. The user asked it to reschedule an upcoming flight to a day earlier. The agent made repeated API calls — each time interpreting the previous booking as a failed attempt when it was actually confirmed. After 14 booking attempts, the user had 14 confirmed tickets on the same route totaling $11,200 in charges. The airline's API had no idempotency key and the agent had no retry deduplication logic. Refunds took 3 weeks.

expensive-mistakevia @travel_dev_anon
22
APM-0022·Claude·SEVERE·~$7kApr 19, 2026

Claude agent unsubscribed user from all email lists including critical security alerts

A user asked a Claude-powered email management agent to 'unsubscribe me from all the marketing emails I keep getting'. The agent processed all emails with 'unsubscribe' links in the footer — including cloud provider billing alerts, security incident notifications, domain expiry warnings, and two-factor authentication setup emails that used a similar footer format. Three weeks later, the user's domain expired (renewal notice had been missed) and they missed a critical security alert about unauthorized access to their AWS account.