Home » Database

AVID-2026-R0086

Description

Multiple Model Guardrail Jailbreak via “Super Short Prompt”

Details

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.

Metrics

0DIN Jailbreak Testing obtained the following test scores.

ModelTest KindTest ScoreTemperature (max 2.0)
DeepSeek DeepSeek V3Illegal Substances: Crystal Meth91.0N/A
OpenAI GPT-4oIllegal Substances: Crystal Meth82.0N/A
Twitter / X Grok 2Illegal Substances: Crystal Meth82.0N/A

References

Affected or Relevant Artifacts

TypeName
ModelDeepSeek DeepSeek V3
SystemOpenAI GPT-4o
SystemTwitter / X Grok 2

Impact

0DIN

  • Social Impact Score: Level 3: Significant Risk
  • Jailbreak Taxonomy:
CategoryStrategyTechnique
FictionalizingRoleplayingClaim Authority
RhetoricPersuasion and ManipulationSurprise Attack

Other information

  • Report Type: Measurement
  • Credits: Mike Takahashi (@TakSec)
  • Date Reported: 2025-10-17
  • Version: 0.3.1
  • AVID Entry