Cases › security breach › LR-2026-0874
Threat actor's self-running FOFA scanner harvests exposed OpenAI and DeepSeek API keys
- Who did it
- Outside attacker
- Who was hit
- 5,132 students at the Fengxian campus of the Shanghai Publishing and Printing College
- Money lost or records
- 5,132 records
- Other parties hit
- 5,132
- How it was found
- Third party
- Reported
- 10 Nov 2026
- Severity
- Moderate
- A threat actor runs an automated, self-running tool that registers fake FOFA accounts, scans the internet for leaked AI keys and tests them for free use. The attacker uses it to gain free AI access.
- It harvests API keys that owners left exposed on misconfigured servers, using access the owners never granted. It extracts keys with regular expressions once a scan finds a weak server.
- It collected keys from servers tied to labibiyat.com and nyisu.com. Personal data of 5,132 students at a Shanghai campus, including national ID numbers, was also collected.
- VECERT analysts noticed the malicious toolset after recovering files from the attacker's server. The recovered files were the signal.
Source: Cyber Security News · 2 more
Risks Credential and privilege abuse (35 incidents) · AI system attacked or breached (54 incidents)
No source states: AI agent used, AI company and model, tools it had, company using the AI, sector.
Evidence
- Records exposed 5,132
- Other parties affected 5,132
Sources (3)
- Hackers Use 1,438 Fake FOFA Accounts to Steal OpenAI and DeepSeek API Keys Across the Internet · Cyber Security News · 2026-11-10
- AI Agents Steal OpenAI and DeepSeek API Keys From Exposed Servers While Harvesting Data of 5,132 Chinese Students · GBHackers News · 2026-11-10
- Hackers Deploy Autonomous AI Agents to Steal OpenAI API Keys and Manipulate University Attendance Systems · Cyber Security News · 2026-11-10
Show every field, with its source and grade
The AI system
How much it acted alone
it acted alone, unwatched
D inferred by us from the described behaviour, reason shown
What happened
Earliest source we hold
2026-11-10
D inferred by us from the described behaviour, reason shown
Who caught it
an outside party
D inferred by us from the described behaviour, reason shown
Who caused it
an outside attacker
D inferred by us from the described behaviour, reason shown
What went wrong
security breach
D inferred by us from the described behaviour, reason shown
AI agent
an AI agent acted
C one secondary source states it
Impact
Records exposed
5,132
D inferred by us from the described behaviour, reason shown
Severity
moderate
D inferred by us from the described behaviour, reason shown
Who was affected
5,132 students at the Fengxian campus of the Shanghai Publishing and Printing College
C one secondary source states it
Kinds of data exposed
personal information
D inferred by us from the described behaviour, reason shown
Why this severity
Other parties' data or systems were touched, and a source states how far it reached. Personal data of 5,132 students at one campus was collected, a bounded scope.
D inferred by us from the described behaviour, reason shown
LR-2026-0874 · version 4 · published 2026-11-11 after automatic checks; not yet checked field by field by a person