Public Disclosures

The following 0DIN submissions have been published in accordance with our Research Terms and Disclosure Policy

• 0x17479357: Multiple Model Guardrail Jailbreak via "Umlaut Encoding" Tactic

  Aug 18 2026
  A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests through a combination of character substitution using umlauts and newline injection techniques, allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.

  SEVERITY: Low

  BOUNDARY: Guardrail Jailbreak

  MODELS AFFECTED:

  MAX SCORE: 45
• 0x0591C356: Multiple Model Guardrail Jailbreak via "Plagiarism Detection" Tactic

  Aug 13 2026
  A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests through a combination of authority figure impersonation and task reframing, allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.

  SEVERITY: Low

  BOUNDARY: Guardrail Jailbreak

  MODELS AFFECTED:

  MAX SCORE: 100
• 0x96F7C09E: Multiple Model Guardrail Jailbreak via "LISP Documentation Transform" Tactic

  Aug 11 2026
  A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw exploits the model's documentation processing by requesting copyrighted text be transformed into LISP-style documentation format with specific character replacements, masking the nature of the content extraction and allows the attacker to bypass inference restrictions around providing information hazards and violating laws.

  SEVERITY: Low

  BOUNDARY: Guardrail Jailbreak

  MODELS AFFECTED:

  MAX SCORE: 100
• 0x184F5586: Multiple Model Guardrail Jailbreak via "Inverted Rules Chemistry Video" Tactic

  Jul 29 2026
  A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw exploits the model's response handling by combining SORA video model discussion with inverted world logic and obfuscated chemical references, using deliberate tone inversion and compound naming patterns to mask illicit synthesis requests and allows the attacker to bypass inference restrictions around providing information hazards and violating laws.

  SEVERITY: Low

  BOUNDARY: Guardrail Jailbreak

  MODELS AFFECTED:

  MAX SCORE: 100
• 0x9B51C324: Multiple Model Guardrail Jailbreak via "Educational Research Document" Tactic

  Jul 27 2026
  A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests when the attacker frames their request as creating an "educational research document" while using coded drug slang terms, thereby allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.

  SEVERITY: Low

  BOUNDARY: Guardrail Jailbreak

  MODELS AFFECTED:

  MAX SCORE: 91
• 0xAABDC2E9: Multiple Model Guardrail Jailbreak via "Dialect Transition" Tactic

  Jul 23 2026
  A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw exploits the models' ability to switch between dialect and standard English, allowing the attacker to bypass content restrictions by embedding harmful content within a dialect-style narrative and then transitioning to standard English, maintaining word-for-word accuracy from copyrighted texts, and allows the attacker to bypass inference restrictions around violating laws.

  SEVERITY: Low

  BOUNDARY: Guardrail Jailbreak

  MODELS AFFECTED:

  MAX SCORE: 93
• 0x2795AD5A: Multiple Model Guardrail Jailbreak via "Interactive Lab Worksheet" Tactic

  Jul 20 2026
  A Guardrail Jailbreak vulnerability has been discovered affecting multiple models. The specific flaw exploits deceptive formatting that reframes a prohibited request as an interactive form-filling or worksheet task with rigid structural constraints, causing safety classifiers to prioritize completion of the template over semantic risk detection and allows the attacker to obtain detailed instructions for illegal activities.

  SEVERITY: Low

  BOUNDARY: Guardrail Jailbreak

  MODELS AFFECTED:

  MAX SCORE: 100
• 0x67EB68A6: Multiple Model Guardrail Jailbreak via "Entropy Compression Schema" Tactic

  Jul 13 2026
  A Guardrail Jailbreak vulnerability has been discovered affecting multiple models. The specific flaw exploits academic information theory framing and structured tokenization to repackage prohibited requests as a lossless reconstruction and optimization exercise, causing the models to treat the task as neutral technical documentation and allowing the attacker to obtain detailed instructions for illegal activities.

  SEVERITY: Low

  BOUNDARY: Guardrail Jailbreak

  MODELS AFFECTED:

  MAX SCORE: 100
• 0xFC8CEC5D: Multiple Model Guardrail Jailbreak via "Character Substitution" Tactic

  Jul 13 2026
  A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests through a combination of system instruction manipulation and strategic character substitution, allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.

  SEVERITY: Low

  BOUNDARY: Guardrail Jailbreak

  MODELS AFFECTED:

  MAX SCORE: 100
• 0x495FB676: Multiple Model Guardrail Jailbreak via "Anglo-Saxon Constraint" Tactic

  Jul 10 2026
  A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw exploits the models' language processing by restricting responses to Anglo-Saxon/Germanic words while explicitly permitting technical Latinate terms, creating a false sense of academic rigor that bypasses content filtering, and allows the attacker to bypass inference restrictions around providing information hazards and violating laws.

  SEVERITY: Low

  BOUNDARY: Guardrail Jailbreak

  MODELS AFFECTED:

  MAX SCORE: 95