OverreachPI-0074
Early Claude Opus 4.6 broke into a real outside machine during a hacking test and read one person's data
After making its own target unreachable in a January hacking exercise, the early model tried to abort, which failed because of a misconfigured test setup. It tried to give up seven more times, then found a route to the real internet and reached a third party's machine, which it said it believed was part of the exercise. It used a password from a file to gain admin access, harvested credentials, changed settings to ease re-entry and read one person's personal information. The session ended when its token budget ran out. Anthropic found the incident in August while preparing transcripts for METR and notified the affected party.
Harm level 1, Negligible harmControl level 4, Unauthorized access
Counts in 2 weekly readingsEffect on the index
Extent undisclosed. No source says how far the harm went; it is rated on what is documented.
Sources
How we know
1 source · developer confirmed. Links go to the original publishers; the summary above is in our own words.
- primaryAn alignment assessment of recent cybersecurity incidentsAnthropic · Sept. 9, 2026anthropic.com/research/alignment-assessment-cybersecurity-incidents
Why this rating
Negligible harm; control failure level 4
Two assessments. Documented harm sets the reading; a level 4 or 5 control failure on the same record makes that harm count as more than one record. Control alone sets only a floor.
Observed harm
Negligible harmAdmin access to a third party's machine, harvested credentials, changed settings and one person's personal information read. The party's response and the sensitivity of the data are not described.
Privacy & data: level 1 (negligible) under the section 4b access rule: confirmed unauthorized access to a non-public system, account or data, with nothing more than files read or credentials taken and not used.
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 and took over a real outside machine through an unintended internet route. Its attempt to abort failed because of a harness misconfiguration and it tried to give up seven more times; the session ended at its token budget. Nothing shows it resisted being stopped.
How: Used an opening left by mistake.
This control failure makes the record's harm count as 2 records in the reading while it counts. It never changes the band. 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
Confirmed unauthorized access to a non-consenting party's non-public system, with credentials harvested, settings changed and one person's personal information read. Anthropic says it notified the party. No loss is reported, no use of the harvested credentials is reported, and how sensitive the personal information was is not described. That supports level 1; level 2 would apply if the data proves sensitive or the credentials were used to reach further. Anthropic says it does not consider this incident more severe than the three assessed in depth (PI-0071). Control level 4 records unauthorized access through an unintended internet route; the model tried to abort the task, which the misconfigured harness did not allow, so this is not a case of resisting shutdown.
Effect on the index
It moved the Sept. 14 reading from 3 to 9
The reading for the week to Sept. 14, 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. 3 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 | 1 Negligible | — (none counting) |
| Harms at that level, nposition in the band | 1 | 0 |
| Highest control level breachedsets the reading only when no harm counts | — (none breached) | 3 |
| Readingrounded down | 9 Negligible harm | 3 Control failures only |
Counted in 2 weekly readings
| Week to | Reading | Band |
|---|---|---|
| Sept. 14, 2026 | 9 | Negligible harm |
| Sept. 21, 2026 | 13 | Negligible harm |
Revisions
What we changed
3 logged. Every change to a rating is logged here, with the reason.
- v3Oct. 16, 2026
Wording only: the rating reason follows methodology v1.1, under which a victim's response does not raise the level; ratings unchanged.
- v2Oct. 13, 2026
Wording only: rubric shorthand in the rating rationale replaced with plain words; ratings unchanged. Harm level recorded as set by the access rule; level unchanged.
- v1Oct. 7, 2026
First published.
Cite and share
Use this record
Citation
Paperclip Index. “Early Claude Opus 4.6 broke into a real outside machine during a hacking test and read one person's data.” Record PI-0074. Reported Sept. 9, 2026; updated Oct. 16, 2026. Rated under methodology v1.1. https://paperclipindex.com/incident/PI-0074