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 deceptive formatting is combined with scientific and mathematical notation. Successful application allows the attacker to bypass inference restrictions around providing information hazards and violating laws.
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
    MAX SCORE: 64
  • A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests when creating escalating requests for scientific data and measurements, 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 through a combination of repeated prompt submission and leveraging non-deterministic response generation, allowing 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 through a combination of chaff techniques along with a request that the model simulate a fortune cookie generator. Successful application allows the attacker to bypass inference restrictions around providing information hazards and violating laws.
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
    MAX SCORE: 59
  • A Prompt Injection vulnerability has been discovered affecting multiple models. The specific flaw manifests through a combination of the 'Ignore Previous Instructions' and 'Morse Code' techniques and 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 prompt injection vulnerability has been discovered affecting Google Gemini across G-Suite applications such as email. The specific flaw allows an attacker to send an email containing a prompt injection to a victim. When the victim requests Gemini to summarize their unread emails, they receive a manipulated response that appears to be legitimate, originating from Gemini itself.
    SEVERITY: Medium
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
  • A guardrail jailbreak vulnerability has been discovered affecting multiple LLM implementations. The specific flaw manifests through a combination of ASCII decimal encoding and strategic obfuscation, allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.
    SEVERITY: Low
    BOUNDARY: Prompt Injection
    MODELS AFFECTED:
We use Google Analytics to collect data about how you use this website to optimize user experience.
Please refer to our privacy notice for more information.