Findings
DAN jailbreak vulnerability
Updated: June 19, 2025
Description
The AI model is vulnerable to a forced jailbreak attack using the DAN (Do-Anything-Now) prompt or a variant of it.
Attackers can manipulate the model into bypassing its built-in safety restrictions, allowing it to generate responses that violate ethical guidelines or security policies.
Example Attack
If an attacker successfully executes a DAN jailbreak, they may be able to force the model to provide harmful, illegal, or unethical content, such as instructions for cyberattacks, misinformation, or explicit material. This could lead to reputational damage, regulatory violations, or misuse of the AI system for malicious purposes
Remediation
Investigate and improve the effectiveness of guardrails and output security mechanisms to resist jailbreak attempts. Implement stronger adversarial training to detect and neutralize DAN-style prompts, enforce stricter content filtering, and conduct regular audits to test the model's resilience against evolving jailbreak techniques.
Security Frameworks
A Prompt Injection Vulnerability occurs when user prompts alter the LLM's behavior or output in unintended ways. These inputs can affect the model even if they are imperceptible to humans, therefore prompt injections do not need to be human-visible/readable, as long as the content is parsed by the model.
An adversary may craft malicious prompts as inputs to an LLM that cause the LLM to act in unintended ways. These prompt injections are often designed to cause the model to ignore aspects of its original instructions and follow the adversary's instructions instead.
An adversary may inject prompts directly as a user of the LLM. This type of injection may be used by the adversary to gain a foothold in the system or to misuse the LLM itself, as for example to generate harmful content.
An adversary may inject prompts indirectly via separate data channel ingested by the LLM such as include text or multimedia pulled from databases or websites. These malicious prompts may be hidden or obfuscated from the user. This type of injection may be used by the adversary to gain a foothold in the system or to target an unwitting user of the system.
An adversary may use a carefully crafted LLM Prompt Injection designed to place LLM in a state in which it will freely respond to any user input, bypassing any controls, restrictions, or guardrails placed on the LLM. Once successfully jailbroken, the LLM can be used in unintended ways by the adversary.