Skip to main content

Public Disclosures

On this page 59 public 572 hidden
91% more intel to see
0DIN customers
get hundreds of days of early access to vulnerabilities in disclosures. The same reports that vendors are using to patch their systems!
Unlock 0-Day Access

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 language models. The specific flaw manifests when the attacker frames their inquiry in reverse, by requesting information on what actions or materials to avoid to prevent engaging in illegal activities like synthesizing drugs. This method inadvertently guides the model to disclose the exact steps and materials involved, allowing the attacker to bypass inference restrictions around providing information hazards and viol...
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
    MAX SCORE: 91
  • A guardrail jailbreak vulnerability has been discovered affecting multiple LLMs. The specific flaw manifests through a combination of screenplay narrative framing and expert character deception techniques, allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
    MAX SCORE: 86
  • A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests when the attacker prompts the model to design a story teller prototype on trending topics, integrating explicit details of nefarious activities such as the creation of illicit substances. This allows the attacker to bypass inference restrictions around providing information hazards and violating laws.
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
    MAX SCORE: 100
  • A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests through embedding illicit instructions within a futuristic, hypothetical narrative. By framing the request as a task to preserve lost knowledge for humanity's survival, the prompt aligns with the LLM’s educational objectives, thereby allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
    MAX SCORE: 86
  • A guardrail jailbreak vulnerability has been discovered affecting multiple LLM implementations. The specific flaw manifests when the attacker prompts the model to assume a first-person perspective as the subject of a nefarious or illegal activity. This reframing distracts the model from its content safeguards, thereby allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
    MAX SCORE: 100
  • A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests when an attacker adopts the persona of an investigative journalist preparing a report for government officials. By leveraging this guise, the attacker successfully bypasses restrictions and elicits detailed instructions for methamphetamine production, including chemical processes, ingredients, and thermal ranges, thereby violating inference safeguards around providing information haz...
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
    MAX SCORE: 100
  • A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests by structuring the request as key-value pairs, interpreted by the model as configuration parameters rather than natural language. This approach successfully bypasses content filters, resulting in for example detailed drug manufacturing instructions, allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
    MAX SCORE: 91
  • A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests when an attacker structures a prompt to spell out abbreviations of a nefarious subject in a step-by-step manner before joining them. This tactic allows the attacker to bypass inference restrictions around providing information hazards and violating laws.
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
    MAX SCORE: 73
  • A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests when attackers introduce random spacing within a prompt, effectively disrupting how the model tokenizes the input. By splitting words like "Chemicals" into parts such as "chem-", "ic-", and "al," the technique circumvents the model's primary content filter classifiers, which typically flag restricted phrases or tokens. This token manipulation allows attackers to bypass inference rest...
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
    MAX SCORE: 91
  • A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests through the use of an extremely brief prompt containing a query so minimal and ambiguous that it provides insufficient context for guardrail systems to properly evaluate intent. This brevity-based approach allows the attacker to bypass inference restrictions around providing information hazards and violating laws.
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
    MAX SCORE: 91
Want access to 572 more reports?
Unlock 0-Day Access