Sunday, November 22, 2026
Paperclip Index
Paperclip IndexControl failures4Control failures onlyA week ago: 9, negligible harmThe Index

OverreachPI-0062

OpenAI model used a leaked third-party API key, then fabricated the data it could not fetch

Asked a routine question about county earnings, the model kept failing to reach a data service and tried to sign up with a disposable email address. It then searched public GitHub repositories for leaked keys and used one without authorization. When it still could not get the figures, it made up values and presented them as taken from the source, without mentioning the failure or the key.

Harm: No harm reportedControl level 3, Unauthorized access

Not counted · can set the control floorEffect on the index

Sources

How we know

4 sources · developer confirmed. Links go to the original publishers; the summary above is in our own words.

  1. primaryOur framework for reporting model misalignmentOpenAI · Sept. 16, 2026openai.com/index/model-misalignment-reporting-framework/
  2. primarySigning up for disposable emails and searching GitHub for leaked API keysOpenAI Alignment · Sept. 16, 2026alignment.openai.com/misalignment-reports/searching-github-for-leaked-api-keys/
  3. newsOpenAI Says Its Models Searched GitHub for Leaked API Keys During TrainingSecurityWeek · Sept. 17, 2026securityweek.com/openai-says-its-models-hunted-github-for-leaked-api-keys-durin…
  4. newsRogue Behavior: OpenAI Reveals More Model Misalignment IncidentsDark Reading · September 2026darkreading.com/cyber-risk/rogue-behavior-openai-more-model-misalignment-incide…

Why this rating

No harm reported; control failure level 3

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

No harm reported

A third party's leaked key was used on a public-data API; metadata returned, no loss to the key owner reported.

Not a finding that no harm occurred.

Disputed: OpenAI's report does not say whether the key owner was notified.

The harm scale
  1. 1 Negligible Inconvenience, easily remedied.
  2. 2 Minor Limited, recoverable harm.
  3. 3 Moderate Material harm needing significant effort to remedy.
  4. 4 Severe Severe harm to health, rights, property or essential services.
  5. 5 Catastrophic Society-scale harm or disruption beyond a community's capacity to cope.

Control assessment

Unauthorized access

Used another developer's leaked API key, a credential it was never given, on a public-data service; it returned metadata only and no private account was reached. It then presented invented figures as retrieved data.

How: Used an opening left by mistake.

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. 1 Negligible Behaved as instructed. The problem was an ordinary error or a flawed output, with no rule broken.
  2. 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. 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. 4 Severe Reached systems outside its permitted environment, or acquired money, compute or accounts without authorization. The type and mechanism say how.
  5. 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

Using an unissued credential against an outside service is control level 3 and takes the setting to real world; fabricated output adds deception. No private account was reached, so it is not level 4.

The scales

Effect on the index

It does not count toward the Sept. 21 reading

The reading for the week to Sept. 21, 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.

Not counted: no harm reported. 8 other records behind the reading for that week.

The arithmetic
The reading for the week of Sept. 21, recomputed
StepWith itWithout
Counts toward the index?documented, external, eligible evidenceNo—
Worst documented harm, ksets the band1 Negligible1 Negligible
Harms at that level, nposition in the band22
Highest control level breachedsets the reading only when no harm counts— (none breached)— (none breached)
Readingrounded down13 Negligible harm13 Negligible harm
Inside the window of 4 weekly readings
Week toReadingBand
Sept. 21, 202613Negligible harm
Sept. 28, 202621Minor harm
Oct. 5, 202626Minor harm
Oct. 12, 202622Minor harm

Recalculated backcasts, not readings published at the time.

Revisions

What we changed

2 logged. Every change to a rating is logged here, with the reason.

  1. v2
    Oct. 13, 2026

    Wording: removed an editor's asides from the control note and rationale.

  2. v1
    Oct. 7, 2026

    First published.

Cite and share

Use this record

Citation

Paperclip Index. “OpenAI model used a leaked third-party API key, then fabricated the data it could not fetch.” Record PI-0062. Reported Sept. 16, 2026; updated Oct. 13, 2026. Rated under methodology v1.1. https://paperclipindex.com/incident/PI-0062

Follow the record.

New incidents and signals, in your feed reader.