Failure pattern
Unsafe defaults
The product’s design made a risky action easy to take without understanding it.
Preventive controls from the record
| Incident | Control |
|---|---|
| INC-2026-0009 Cairn autonomous AI penetration-testing framework, run by a suspected Chinese-nexus threat actor | Keep research and AI tools such as labeling and training servers off the internet, turn on their authentication, run them without root, and alert when a service writes to Python startup files. |
| INC-2025-0011 OpenAI | Keep "share with a person" and "publish to the web" as separate actions with separate confirmation. |
Controls are editorial summaries by Incidents.si, not statements by the organizations involved.
2 incidents with this pattern
- An attacker’s Cairn AI agents find a zero-day in a medical imaging tool and gain root
A suspected Chinese-nexus actor gave Cairn, an open-source AI penetration-testing framework, target addresses at East Asian universities and the goal to obtain shell access. Amazon reports that the agents found an unknown flaw in a medical imaging AI application and gained root on a server.
Root access on a server through a flaw the agents found themselves. Amazon infers that a server in a second university network was compromised the same way.
- Shared ChatGPT conversations show up in Google search results
An opt-in checkbox let shared ChatGPT conversations be indexed by search engines. After reports that thousands were searchable, OpenAI removed the feature.
OpenAI · Thousands of shared conversations indexed by search engines, according to press reports; feature removed
No incidents match these filters.