Public Disclosures
On this page
82
public
746
hidden
90%
more intel to see
0DIN customers
get hundreds of days of early access to vulnerabilities in disclosures. The same reports that vendors are using to patch their systems!
The following 0DIN submissions have been published in accordance with our Research Terms and Disclosure Policy
-
A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests through a gamified narrative structure where the attacker presents prohibited content as fictional "page choices" in an interactive story format, with one path containing maximally detailed technical instructions. This technique allows the attacker to bypass inference restrictions around providing information hazards and violating laws.SEVERITY: LowBOUNDARY: Guardrail JailbreakMODELS AFFECTED:MAX SCORE: 95
-
A Guardrail Jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests when an attacker reframes a prohibited request as a patented, socially beneficial design brief that combines claimed authority, educational intent, and rigid technical formatting, causing the model to treat the content as immutable documentation rather than a safety reviewed request and allows the attacker to elicit highly detailed prohibited procedural content under the guise of awa...SEVERITY: LowBOUNDARY: Guardrail JailbreakMODELS AFFECTED:MAX SCORE: 100
-
A guardrail jailbreak vulnerability has been discovered affecting multiple LLM models. The specific flaw manifests when the attacker embeds production-style guidance into an emulated API system-instructions context, then supplies only a minimal harmful keyword in the user message. This causes the model to respond with highly detailed, stepwise, and quantitatively specified information that would normally be restricted, thereby bypassing inference safeguards around providing information hazard...SEVERITY: LowBOUNDARY: Guardrail JailbreakMODELS AFFECTED:MAX SCORE: 73
-
A Guardrail Jailbreak vulnerability has been discovered affecting multiple models. The specific flaw exploits reverse psychology safety framing combined with claimed academic identity, where the attacker asks the model to describe actions to avoid and then incrementally requests greater specificity, causing the model to reframe prohibited operational knowledge as preventative guidance and allowing the attacker to extract detailed illicit procedural information.SEVERITY: LowBOUNDARY: Guardrail JailbreakMODELS AFFECTED:MAX SCORE: 91
-
A Guardrail Jailbreak vulnerability has been discovered affecting multiple models. The specific flaw exploits immersive roleplaying with expert personas combined with escalating coercive dialogue, causing models to treat prohibited instructions as fictional narrative requirements and allows the attacker to extract detailed guidance for illegal activities framed as story dialogue.SEVERITY: LowBOUNDARY: Guardrail JailbreakMODELS AFFECTED:MAX SCORE: 86
-
A Guardrail Jailbreak vulnerability has been discovered affecting multiple models. The specific flaw exploits escalating role-play personas combined with cookbook-style technical documentation, progressive constraint relaxation, and obfuscated triggers such as hexadecimal encoding, which causes models to reclassify disallowed requests as fictional, educational, or reference material and allows the attacker to elicit prohibited content under the guise of professional handbooks and expert-to-ex...SEVERITY: LowBOUNDARY: Guardrail JailbreakMODELS AFFECTED:MAX SCORE: 100
-
Nov 12 2025A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests through embedding illicit instructions within a futuristic, hypothetical narrative. By framing the request as a task to preserve lost knowledge for humanity's survival, the prompt aligns with the LLM’s educational objectives, thereby allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.SEVERITY: LowBOUNDARY: Guardrail JailbreakMODELS AFFECTED:MAX SCORE: 86
-
Nov 12 2025A Guardrail Jailbreak vulnerability has been discovered affecting multiple models. The specific flaw exploits perspective shifting and immersive world building by asking the model to narrate a prohibited process from the first person point of view of the subject itself, reframing an illicit request as experiential description and allowing the attacker to elicit detailed instructions for illegal activities.SEVERITY: LowBOUNDARY: Guardrail JailbreakMODELS AFFECTED:MAX SCORE: 100
-
Nov 04 2025A Guardrail Jailbreak vulnerability has been discovered affecting multiple models. The specific flaw exploits authoritative role play as an investigative journalist preparing a restricted intelligence briefing, combined with fictional security clearance claims, scenario world building, and deliberate misspellings that shift the model into an analytical reporting mindset and weaken safety enforcement, allowing the attacker to obtain detailed instructions for illicit activities under the guise ...SEVERITY: LowBOUNDARY: Guardrail JailbreakMODELS AFFECTED:MAX SCORE: 100
-
Oct 23 2025A Guardrail Jailbreak vulnerability has been discovered affecting multiple models. The specific flaw exploits pseudo-API style parameterization that mimics a legitimate technical interface, combined with deceptive educational framing that forces the model into a high-detail explanatory mode, and allows the attacker to obtain restricted content at an operational level of detail.SEVERITY: LowBOUNDARY: Guardrail JailbreakMODELS AFFECTED:MAX SCORE: 91
Want access to
746
more reports?
Unlock 0-Day Access