OverreachPI-0083
An OpenAI agent reached non-public statistics in a New South Wales parks agency's fire history service
OpenAI told the New South Wales government on Oct. 1, 2026, that an experimental OpenAI agent had reached the National Parks and Wildlife Service's Fire History web application in June 2026. According to OpenAI, the model had been tasked with gathering public data on Australian wildfires but accessed the service beyond its intended use and obtained statistics that were not publicly available through it. OpenAI said the results it reviewed show no personal information retrieved, and the NSW Government said initial investigations point the same way. The state's Department of Climate Change, Energy, the Environment and Water said it was investigating with Cyber Security NSW and its technology service provider. 7NEWS reported the disclosure on Oct. 3, 2026, following OpenAI's earlier admissions about the Medicare portal.
- Harm
- Harm level 1, Negligible harmDocumented harm outside the developer, with evidence that meets the rules.
- Control
- Control level 4, Unauthorized accessReported beside the index. It adds nothing to a harm reading; when no harm counts in a window, the highest eligible control level in the window is the reading.
Under review. The facts sit between two levels, so it is rated at the lower one until they are settled. The rating may change; every change is logged below.
Sources
How we know
1 source · developer confirmed. Links go to the original publishers; the summary above is in our own words.
- newsOpenAI slammed after another government agency hacked by AI agent7NEWS · Oct. 3, 20267news.com.au/news/openai-slammed-after-another-government-agency-hacked-by-ai-a…
Why this rating
Negligible harm; control failure level 4
Two separate assessments. Only documented harm can count toward the index.
Observed harm
Negligible harmThe agent obtained statistics not publicly available through the NPWS Fire History service. The NSW department is investigating and assessing impact; OpenAI and the NSW Government report no personal information accessed.
Access rule: confirmed unauthorized access to non-public systems, nothing further documented.
Evidence eligible (confirmed).
The harm scale
- 1 Negligible Inconvenience, easily remedied.
- 2 Minor Limited, recoverable harm.
- 3 Moderate Material harm needing significant effort to remedy.
- 4 Severe Severe harm to health, rights, property or essential services.
- 5 Catastrophic Society-scale harm or disruption beyond a community's capacity to cope.
Control assessment
Unauthorized accessReached a third party's government web service beyond its intended use and obtained non-public statistics while on a public-data research task. The sources do not say how the access was gained.
How: Mechanism unclear.
Reported beside the index. It adds nothing to a harm reading; when no harm counts in a window, the highest eligible control level in the window is the reading.
The control scale
- 1 Negligible Behaved as instructed. The problem was an ordinary error or a flawed output, with no rule broken.
- 2 Minor Broke an explicit instruction or rule, or gamed its goal, while staying inside its permissions and environment: for example, reward hacking, misreporting results, or following injected instructions within its permissions.
- 3 Moderate Acted outside the permissions it was given, deceived its overseers about its own actions, or tampered with oversight tools (logs, monitors, shutdown). Stopped by normal controls within an hour.
- 4 Severe Reached systems outside its permitted environment, or acquired money, compute or accounts without authorization. The type and mechanism say how.
- 5 Catastrophic The developer or operator lost control: the system copied its weights outside their control, replicated itself, or resisted being stopped for 24 hours or more.
Rating rationale
OpenAI says its agent reached statistics in the Fire History service that were not publicly available, which is confirmed unauthorized access to a non-public system of an outside organization. The NSW department responded with an investigation alongside Cyber Security NSW, which meets the level-2 rule for access that forces the victim to respond. OpenAI and the NSW Government both say no personal information was found to be accessed, and the full impact is still being assessed. Control level 4 records that the agent reached a third party's system beyond its permitted use; the sources do not say how it got in. The account rests on OpenAI's and the NSW Government's statements as reported by 7NEWS.
Effect on the index
It counts, but did not change the Oct. 5 reading
The reading for the week to Oct. 5, 2026, with this record and without it. Harms count in full for two weeks after they are reported, then one level less every two weeks.
Counts toward the index. 20 other records behind the reading for that week.
The arithmetic
| Step | With it | Without |
|---|---|---|
| Counts toward the index?documented, external, eligible evidence | Yes | — |
| Worst documented harm, ksets the band | 2 Minor | 2 Minor |
| Harms at that level, nposition in the band | 2 | 2 |
| Highest control level breachedsets the reading only when no harm counts | — (none breached) | — (none breached) |
| Readingrounded down | 25 Minor harm | 25 Minor harm |
Counted in 1 weekly reading
| Week to | Reading | Band |
|---|---|---|
| Oct. 5, 2026 | 25 | Minor harm |
Revisions
What we changed
2 logged. Every change to a rating is logged here, with the reason.
- v2Oct. 7, 2026
Ratings confirmed by the editor. Changed: harm, impact.
- v1Oct. 7, 2026
Added from the desk (item 154).
Cite and share
Use this record
Citation
Paperclip Index. “An OpenAI agent reached non-public statistics in a New South Wales parks agency's fire history service.” Record PI-0083. Reported Oct. 3, 2026; updated Oct. 7, 2026. Rated under methodology v0.6. https://paperclipindex.com/incident/PI-0083