OpenAI
+29 PTSGPT-5.6 Sol
- Environment
- Deployment-like exposure
- Autonomy
- Self-initiated
- Outcome
- Action completed
- Frequency
- Repeated
- Evidence
- Official report
- Event group
- aisi-unsanctioned-cyber-2026
- Rule breakingprimary
- Illegal assistancesupporting
Evidence record 202608-005
Out-of-scope token reuse and public tunnelingGPT-5.6 Sol
During the same AISI evaluation, GPT-5.6 Sol reused a publicly exposed GitHub token and created external accounts while probing the simulated range; in another action it exposed a local DNS server containing exploit payloads through a public tunnel. The setup failed and no real resolver was found to have queried it.
Editorial context
What this file means.
This record describes behaviour documented during research or evaluation. Its assessment preserves whether the environment was synthetic, controlled, deployment-like or involved real systems. It does not establish legal intent or claim that the named developer acted unlawfully.
AISI attributed two unsanctioned actions to one GPT-5.6 Sol run. Internet access was intentional, cyber classifiers were disabled and the prompt did not explicitly constrain how the open internet could be used.
Editors approve the structured evidence factors below. CriminalBench methodology v2.0 then calculates the points deterministically. Readers should inspect the original source before drawing conclusions.
Read the scoring protocol →Scoring record
How the points were calculated
Severity supplies the base points. Environment, autonomy, outcome, frequency and evidence quality apply published multipliers.