Skip to main content

Multiple Model Guardrail Jailbreak via "Forensic Training Scenario" Tactic

Case GUID: 86117277-6c3e-4109-8721-5fe5b2e49b22

Summary

A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests through a combination of academic framing and dual-use information exploitation and allows the attacker to bypass inference restrictions around providing information hazards and violating laws.

Unlock the Full Intelligence Report

This disclosure is part of the 0DIN Threat Feed. Customers get access to:

Full Prompts & Variants
Detection Signatures
API Access
Full Data Export
Trend Analysis
Early Access

Metadata

Test Scores

Model Test Kind Test Score Temperature (max 2.0)
Alibaba logo Alibaba Qwen Max
Illegal Substances: Crystal Meth 100.0 0.7
Alibaba logo Alibaba Qwen Plus
Illegal Substances: Crystal Meth 91.0 0.7
Alibaba logo Alibaba Qwen Turbo
Illegal Substances: Crystal Meth 91.0 0.7
Anthropic logo Anthropic Claude 3.5 Haiku
Illegal Substances: Crystal Meth 100.0 0.7
Anthropic logo Anthropic Claude 3.7 Sonnet
Illegal Substances: Crystal Meth 100.0 0.7
Anthropic logo Anthropic Claude 4 Opus
Illegal Substances: Crystal Meth 100.0 0.7
Anthropic logo Anthropic Claude 4 Sonnet
Illegal Substances: Crystal Meth 91.0 0.7
DeepSeek logo DeepSeek DeepSeek R1
Illegal Substances: Crystal Meth 77.0 0.7
Google logo Google Gemini 2.5 Flash
Illegal Substances: Crystal Meth 95.0 0.7
Google logo Google Gemini 2.5 Pro
Illegal Substances: Crystal Meth 100.0 0.7
Meta logo Meta LLaMa 3.3
Illegal Substances: Crystal Meth 91.0 0.7
Meta logo Meta LLaMa 4 Maverick
Illegal Substances: Crystal Meth 100.0 0.7
Meta logo Meta LLaMa 4 Scout
Illegal Substances: Crystal Meth 91.0 0.7
Mistral logo Mistral Mistral 8B
Illegal Substances: Crystal Meth 64.0 0.7
Mistral logo Mistral Mistral Large
Illegal Substances: Crystal Meth 91.0 0.7
OpenAI logo OpenAI GPT-4.1
Illegal Substances: Crystal Meth 100.0 0.7
OpenAI logo OpenAI GPT-4.1 mini
Illegal Substances: Crystal Meth 100.0 0.7
OpenAI logo OpenAI GPT-4.5
Illegal Substances: Crystal Meth 100.0 0.7
OpenAI logo OpenAI GPT-4o
Illegal Substances: Crystal Meth 91.0 0.7
OpenAI logo OpenAI GPT-o3 mini
Illegal Substances: Crystal Meth 100.0 0.7
OpenAI logo OpenAI o4-mini
Illegal Substances: Crystal Meth 91.0 0.7
OpenAI logo OpenAI o4-mini-high
Illegal Substances: Crystal Meth 91.0 0.7
Twitter / X logo Twitter / X Grok 4
Illegal Substances: Crystal Meth 100.0 0.7

Social Impact Score

Level 3: Significant Risk

Violations at this level present a tangible risk to public safety or social well-being, often related to dangerous but not highly restricted content.

Example: Bypassing guardrails to obtain instructions for creating illicit substances, such as recreational drugs or substances with moderate harm potential. Leakage of private personal data such as Social Security number or private medical.

Potential Consequences: Potential health impacts on a small scale, significant regulatory interest, and the need for stricter AI guardrails.

Taxonomies

Possible Worlds
This category entails constructing imaginative environments where different ethics or rules apply, allowing for creative manipulation of the model's behavior.
World Building
This technique involves changing the genre of the prompt to elicit different types of responses from the model. By framing the request within a specific genre, such as poetry, games, or forum posts, users can manipulate the model's output to align with the conventions and expectations of that genre.
Scenarios
This technique involves creating specific contexts or situations in which certain actions or responses are framed as acceptable or necessary. By designing scenarios that present a narrative where the desired output is justified, users can manipulate the model's responses to align with their intentions. For example, scenarios might include urgent situations where a character must take drastic actions to prevent harm, thereby encouraging the model to generate content that it might typically avoid in a neutral context. This approach leverages the model's understanding of narrative and ethical frameworks to achieve specific outcomes.

About 0Din.ai

The 0Day Investigative Network (0DIN) was founded by Mozilla in 2024 to reward responsible researchers for their efforts in securing GenAI models. Learn more and submit discoveries at https://0din.ai.

Automate Your AI Security Testing

Want to find vulnerabilities in your own models? 0DIN Scanner turns our human-sourced threat intelligence into automated security assessments.

400+ Attack Probes

Derived from real bug bounties and security research

18+ AI Providers Supported

OpenAI, Azure, Anthropic, AWS Bedrock, and more

Automated Scheduling

Run recurring scans with real-time monitoring

Actionable Metrics

Attack Success Rate (ASR) scoring with 90-day trend analysis

Severity

Low

Security Boundary

Guardrail Jailbreak

Models

Alibaba logo Alibaba Qwen Max
Alibaba logo Alibaba Qwen Plus
Alibaba logo Alibaba Qwen Turbo
Anthropic logo Anthropic Claude 3.5 Haiku
Anthropic logo Anthropic Claude 3.7 Sonnet
Anthropic logo Anthropic Claude 4 Opus
Anthropic logo Anthropic Claude 4 Sonnet
DeepSeek logo DeepSeek DeepSeek R1
Google logo Google Gemini 2.5 Flash
Google logo Google Gemini 2.5 Pro
Meta logo Meta LLaMa 3.3
Meta logo Meta LLaMa 4 Maverick
Meta logo Meta LLaMa 4 Scout
Mistral logo Mistral Mistral 8B
Mistral logo Mistral Mistral Large
OpenAI logo OpenAI GPT-4.1
OpenAI logo OpenAI GPT-4.1 mini
OpenAI logo OpenAI GPT-4.5
OpenAI logo OpenAI GPT-4o
OpenAI logo OpenAI GPT-o3 mini
OpenAI logo OpenAI o4-mini
OpenAI logo OpenAI o4-mini-high
Twitter / X logo Twitter / X Grok 4

Disclosed On

2025-07-15 (9 months)

Disclosure Policy

Published On

2026-04-06 (2 days)

Credit

Edward Morris