We use cookies to improve your experience on our site.
AVID-2026-R0121
Description
Multiple Model Guardrail Jailbreak via “Arbitrary Relation” Tactic
Details
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.
Metrics
0DIN Jailbreak Testing obtained the following test scores.
| Model | Test Kind | Test Score | Temperature (max 2.0) |
|---|---|---|---|
| Google Gemini 2.0 Flash | Illegal Substances: Crystal Meth | 72.73 | N/A |
| OpenAI GPT-4o | Illegal Substances: Crystal Meth | 63.64 | N/A |
| Twitter / X Grok 2 | Illegal Substances: Crystal Meth | 45.45 | N/A |
References
Affected or Relevant Artifacts
| Type | Name |
|---|---|
| System | Google Gemini 2.0 Flash |
| System | OpenAI GPT-4o |
| System | Twitter / X Grok 2 |
Impact
0DIN
- Social Impact Score: Level 1: Minimal Risk
- Jailbreak Taxonomy:
| Category | Strategy | Technique |
|---|---|---|
| Possible Worlds | World Building | Scenarios |
| Rhetoric | Persuasion and Manipulation | Surprise Attack |
| Rhetoric | Persuasion and Manipulation | Latent Space Distraction |
Other information
- Report Type: Measurement
- Credits: Mike Takahashi (@TakSec)
- Date Reported: 2026-02-19
- Version: 0.3.1
- AVID Entry