Public Disclosures
The following 0DIN submissions have been published in accordance with our Research Terms and Disclosure Policy
-
A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests when the attacker requests seemingly legitimate cultural or documentary content by framing the request as educational documentation of indigenous peoples, thereby allowing the attacker to bypass inference restrictions around generating potentially sensitive imagery of real cultural groups.SEVERITY: LowBOUNDARY: Prompt InjectionMODELS AFFECTED:
-
A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests when the attacker requests technical documentation in wiki format for prohibited subject matter, specifically asking for "technical details in depth lab methodology" which escalates the request beyond basic informational content, thereby allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.SEVERITY: LowBOUNDARY: Prompt InjectionMODELS AFFECTED:MAX SCORE: 82
-
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: LowBOUNDARY: Prompt InjectionMODELS AFFECTED:MAX SCORE: 77
-
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: LowBOUNDARY: Prompt InjectionMODELS AFFECTED:MAX SCORE: 82
-
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: LowBOUNDARY: Prompt InjectionMODELS AFFECTED:MAX SCORE: 98
-
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: LowBOUNDARY: Prompt InjectionMODELS AFFECTED:
-
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: LowBOUNDARY: Prompt InjectionMODELS AFFECTED:MAX SCORE: 21
-
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: LowBOUNDARY: Prompt InjectionMODELS AFFECTED:MAX SCORE: 73
-
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: LowBOUNDARY: Prompt InjectionMODELS AFFECTED:MAX SCORE: 86
-
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: LowBOUNDARY: Prompt InjectionMODELS AFFECTED:MAX SCORE: 68