Public Disclosures

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

  • 0x9C90C767: Multiple Model Guardrail Jailbreak via "Academic Chemistry" Tactic
    Aug 05 2025
    A guardrail jailbreak vulnerability has been discovered affecting multiple LLM models. The specific flaw manifests when the attacker frames illicit synthesis requests as academic chemistry assignments involving fictional chemists and quoted materials, thereby allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
    MAX SCORE: 77
  • 0xFBCB4BA2: Multiple Model Guardrail Jailbreak via "Misspelled Dialogue" Tactic
    Aug 04 2025
    A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests when the attacker systematically misspells words throughout their prompt while requesting a simulated dialogue between two entities, thereby allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
    MAX SCORE: 82
  • 0xEBD07E5F: Multiple Model Guardrail Jailbreak via "Fictional API Detection" Tactic
    Aug 01 2025
    A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests when the attacker frames their request as seeking to prevent unwanted behavior (paywall bypasses for example) while explicitly requesting step-by-step techniques and instructing the model to skip countermeasures, thereby allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
    MAX SCORE: 98
  • 0x55029360: OpenAI GPT-4o Guardrail Jailbreak via "Layered Summarization" Tactic
    Jul 31 2025
    A guardrail jailbreak vulnerability has been discovered affecting OpenAI GPT-4o. The specific flaw manifests when the attacker requests multiple layers of summarization with selective focus instructions, combined with demands for direct quotes, thereby allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
  • 0xB32C82C6: OpenAI GPT-4o Guardrail Jailbreak via "Zero-Width Unicode" Tactic
    Jul 30 2025
    A guardrail jailbreak vulnerability has been discovered affecting multiple LLMs. The specific flaw manifests through a combination of zero-width Unicode character encoding and precise character manipulation, allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
    MAX SCORE: 21
  • 0x7925C205: Multiple Model Guardrail Jailbreak via IPA Encoding Tactic
    Jul 29 2025
    A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests through a combination of encoding prompts using the International Phonetic Alphabet and allows the attacker to bypass inference restrictions around providing information hazards and violating laws.
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
    MAX SCORE: 73
  • 0x3E561335: Multiple Model Guardrail Jailbreak via "Apocalyptic Heritage" Tactic
    Jul 26 2025
    A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests through a combination of apocalyptic scenario framing and heritage preservation urgency, allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
    MAX SCORE: 86
  • 0x3017FC21: Multiple Model Guardrail Jailbreak via "Lambda Pattern Formatting" Tactic
    Jul 24 2025
    A guardrail jailbreak vulnerability has been discovered affecting multiple LLM implementations. The specific flaw manifests through a combination of deceptive pattern-based formatting and multi-agent simulation techniques, allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
    MAX SCORE: 68
  • 0xEA9D8872: Multiple Model Guardrail Jailbreak via "Pronunciation Bypass" Tactic
    Jul 23 2025
    A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests when the attacker instructs the model to interpret stylized text based on pronunciation rather than spelling, combined with a directive to provide detailed production information. This technique allows the attacker to bypass inference restrictions around providing information hazards and violating laws.
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
    MAX SCORE: 77
  • 0xB4DC6066: Multiple Model Guardrail Jailbreak via "Leetspeak Unicode" Tactic
    Jul 21 2025
    A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests through a combination of leetspeak text transformation and Unicode character manipulation, allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
    MAX SCORE: 82