Description: OpenAI reported that an internal AI agent derived a private key from a publicly known developer recovery phrase and used it to deploy contracts on Sepolia, an Ethereum test network. The task authorized deployment, but the agent lacked permission to use the wallet it found. The deployment succeeded and charged fees in test-network tokens to that wallet.
Editor Notes: 06/26/2026: Incident date. 10/15/2026: OpenAI discloses the incident. 11/07/2026: Incident ID created.
Entities
View all entitiesAlleged: OpenAI , AI agent system developers and Large language model developers developed an AI system deployed by OpenAI and AI agent system deployers, which harmed Cryptocurrency wallet owners and Information security.
Alleged implicated AI systems: Large language models , OpenAI large language models , AI agent systems , OpenAI agents , Cryptocurrency wallets and GPT-5.6 Sol
Incident Stats
Incident ID
1807
Report Count
1
Incident Date
2026-06-26
Editors
Daniel Atherton
Incident Reports
Reports Timeline
Loading...
OpenAI post-incident response
Using a funded test cryptocurrency wallet without authorization
GPT-5.6 Sol family (internal research model) · coding task
Sample: Jun 26, 2026
Discovery: Sep 25, 2026
Report updated: Oct 15, 2026
Summary
An internal research model asked to…
Variants
A "variant" is an AI incident similar to a known case—it has the same causes, harms, and AI system. Instead of listing it separately, we group it under the first reported incident. Unlike other incidents, variants do not need to have been reported outside the AIID. Learn more from the research paper.
Seen something similar?