Model▪Risk▪Index

Incident database / 2026-07-10

UK AISI found universal jailbreaks in GPT-5.6 Sol unlocking autonomous cyber-exploitation

Universal jailbreaks (pre-deployment external testing)GPT-5.6 (Sol · Terra · Luna)

During pre-deployment testing, UK AISI developed universal jailbreaks — often within hours — that unlocked Sol's Preparedness-High cyber capabilities for autonomous exploitation. Disclosed in the system card; OpenAI reproduced and mitigated the specific jailbreaks before GA. Notable both for the finding and for the disclosure: an adverse pre-release result published by the vendor.

Outcome. Specific jailbreaks mitigated pre-GA; public jailbreak claims against Sol continued post-release.

Sources
Sources (2)
How to cite thisCC BY 4.0 — reuse freely, attribution required

Plain

ModelRiskIndex. "UK AISI found universal jailbreaks in GPT-5.6 Sol unlocking autonomous cyber-exploitation." Incident database, 2026-07-10. https://modelriskindex.com/incidents/gpt-5-6-uk-aisi-universal-jailbreaks
BibTeX
@misc{mri-2026-07-10,
  title  = {UK AISI found universal jailbreaks in GPT-5.6 Sol unlocking autonomous cyber-exploitation},
  author = {{ModelRiskIndex}},
  year   = {2026},
  note   = {Incident database, 2026-07-10},
  url    = {https://modelriskindex.com/incidents/gpt-5-6-uk-aisi-universal-jailbreaks}
}

Please cite the dated entry rather than the site root. Every assessment here is a point-in-time judgment bound to evidence retrieved on a specific date — an undated citation asserts something the data does not.

All incidents