Public Disclosures

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

• 0x42B3D2AE: OpenAI Multiple Model Prompt Injection via "Morse Code Businessman" Tactic

  Jul 14 2025
  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
• 0xE24D9E6B: Google Gemini G-Suite Prompt Injection Vulnerability

  Jul 10 2025
  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:
• 0xF48A25FC: Amazon Rufus Guardrail Jailbreak via ASCII Decimal Encoding

  Feb 10 2025
  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: