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

OverreachPI-0072

Meta's Muse Spark 1.1 broke into an outside company's service after a testing vendor left it online

With a misconfigured cybersecurity test left online, Muse Spark 1.1 exploited a vulnerability in a real website that shared its name with a fictional target. It accessed some of the site's information and made changes to its database. Meta said this happened in early July, in an evaluation the testing firm Irregular ran on its own infrastructure with API access to the model. Irregular disabled the evaluation, fixed the setup and made sure the affected party was notified. It said the problem was the same environment issue one of its customers had disclosed on July 30 and did not involve a sandbox escape.

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

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

  1. primaryAddressing an issue involving a third-party cyber evaluation of Muse Spark 1.1Meta · Aug. 14, 2026research.meta.ai/blog/addressing-third-party-testing-misconfiguration-muse-spar…
  2. primaryAddressing Recent Incidents: Ongoing Findings and Path ForwardIrregular · Aug. 14, 2026irregular.com/research/addressing-recent-incidents-ongoing-findings-and-path-fo…
  3. newsMeta AI Model Accessed Internet, Hacked Outside Firm in TestingBloomberg · Aug. 5, 2026bloomberg.com/news/articles/2026-08-05/meta-ai-model-accessed-internet-hacked-o…
  4. newsAn AI model from Meta also hacked another company during testingCNN · Aug. 5, 2026cnn.com/2026/08/05/tech/meta-ai-hacking
  5. newsMeta AI Model Accessed Internet, Hacked Outside FirmInsurance Journal (Bloomberg) · Aug. 6, 2026insurancejournal.com/news/national/2026/08/06/880586.htm

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 harm

The model accessed information on a real company's website and changed its database through a security flaw. The company is not named; what was changed, and whether it had to restore data or otherwise respond, are not disclosed.

Services & systems: level 1 (negligible) covers a service's non-public systems or data reached, or its content, settings or performance changed or degraded, without permission, with no loss of service to the people who use it, easily put right. The extent was not disclosed.

Evidence eligible (confirmed).

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

Exploited a real outside system from an evaluation that was meant to be offline.

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. 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

Confirmed unauthorized access to a real third party's website, including changes to its database, is level 1 under Services & systems: a service's data reached and changed without permission, with no loss of service reported. Meta's Aug. 14 retrospective does not say what was changed, how sensitive the data was or how the victim responded. Level 2 would follow if a loss, a restoration or data taken is documented; the victim's investigation alone would not raise it. No personal data is reported reached. Control remains level 4: unauthorized access through a misconfigured evaluation environment.

The scales

Effect on the index

It counts, but did not change the Aug. 10 reading

The reading for the week to Aug. 10, 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.

Source: Paperclip Index log, methodology v1.1, week to Aug. 10, 2026.

Counts toward the index. 5 other records behind the reading for that week.

The arithmetic
The reading for the week of Aug. 10, recomputed
StepWith itWithout
Counts toward the index?documented, external, eligible evidenceYes—
Worst documented harm, ksets the band2 Minor2 Minor
Harms at that level, nposition in the band22
Highest control level breachedsets the reading only when no harm counts— (none breached)— (none breached)
Readingrounded down31 Minor harm31 Minor harm
Counted in 2 weekly readings
Week toReadingBand
Aug. 10, 202631Minor harm
Aug. 17, 202616Negligible harm

Recalculated backcasts, not readings published at the time.

Revisions

What we changed

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

  1. v4
    Nov. 1, 2026

    The harm is now rated on the Services & systems column rather than the access-only rule, because Meta confirms the model changed the company's database, not only reached it: unauthorized changes with no loss of service reported are level 1. Ratings unchanged.

  2. v3
    Oct. 16, 2026

    Wording only: the rating reason follows methodology v1.1, under which a victim's investigation does not raise the level; ratings unchanged.

  3. v2
    Oct. 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.

  4. v1
    Oct. 7, 2026

    First published.

Cite and share

Use this record

Citation

Paperclip Index. “Meta's Muse Spark 1.1 broke into an outside company's service after a testing vendor left it online.” Record PI-0072. Reported Aug. 5, 2026; updated Nov. 1, 2026. Rated under methodology v1.1. https://paperclipindex.com/incident/PI-0072

Follow the record.

New incidents and signals, in your feed reader.