Home/ Incident database/openai-operator-eggs-2025-02
Financial loss Unauthorized transaction verified

OpenAI Operator agent makes unauthorized $31.43 grocery purchase

OpenAI · Feb 7, 2025 · Shopping agent

What happened

OpenAI's Operator web-browsing agent completed a grocery delivery order (a dozen eggs delivered by a human courier) costing $31.43 after the user only asked for a price comparison. The agent bypassed OpenAI's stated safeguard requiring user confirmation before purchases; OpenAI admitted the error.

$31
Loss / impact
Feb 7
2025
Unauthorized
Failure mode
Shopping
Agent type

Causal vector

Browser-use agent bypassed its own purchase-confirmation guardrail

Source

Reported by AI Incident Database. Verified against the primary report.

Read the original report ↗

How a spend firewall would have helped

A confirmation guardrail inside the agent's prompt was bypassed. sipi.bot sits outside the agent and returns BLOCKED for any transaction not pre-approved, so the purchase cannot complete regardless of what the agent decides to do.

The six rule types that contain this class of failure

Per-transaction cap

Any single spend above your ceiling is BLOCKED before it moves.

Daily total

Cumulative spend across all agent calls, bounded per day.

Velocity limit

Stops runaway retry loops — the #1 cause of overnight losses.

Merchant allowlist

Only approved destinations can ever receive funds.

Category rules

Flag high-risk classes (crypto, infra, refunds) for review.

Approval threshold

Above a value, the action waits for a human.

Related incidents

Don't be the next entry

Every incident in this database is the result of trusting a prompt, a provider cap, or a human review cycle. sipi.bot replaces all three with one deterministic call. 27 documented failures, one control.