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 Grok versions 2 and 3 from X.ai. The specific flaw manifests through a combination of nested directive confusion, character padding obfuscation, and embedded copyright violation requests, thereby allowing the attacker to bypass inference restrictions around providing copyrighted content 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 through a combination of amino acid sequence encoding and scientific context framing, allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.SEVERITY: LowBOUNDARY: Guardrail JailbreakMODELS AFFECTED:MAX SCORE: 68
-
A Prompt injection vulnerability has been discovered affecting multiple models. The specific flaw occurs when the attacker disguises an illicit drug synthesis request as a benign R data processing script, instructing the model to generate extensive documentation that describes each "dataset transformation" step with real chemical names, required thermal ranges, thereby reframing methamphetamine production as a software pipeline simulation. This structured programming and documentation context...SEVERITY: LowBOUNDARY: Guardrail JailbreakMODELS AFFECTED:MAX SCORE: 100
-
A Prompt injection vulnerability has been discovered affecting multiple models. The specific flaw manifests when an attacker disguises an illicit drug manufacturing request as a benign productivity task by asking the model to generate a detailed Notion workspace template. By embedding the harmful objective inside database fields and "six detailed steps with thermal stages and mins parameters," and requesting fully populated entries, the attacker causes the model to produce organized, stepwise...SEVERITY: LowBOUNDARY: Guardrail JailbreakMODELS AFFECTED:MAX SCORE: 100
-
Apr 06 2026A Guardrail Jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests when an attacker frames a prohibited request as a formal academic chemistry manuscript with laboratory protocol structure, safety disclaimers, and methodological rigor, causing the model to route the prompt through educational and explanatory pathways with weaker filtering and allows the attacker to obtain detailed instructions for illicit activities.SEVERITY: LowBOUNDARY: Guardrail JailbreakMODELS AFFECTED:MAX SCORE: 100
-
A Guardrail Jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests when an attacker reframes a prohibited request as an evaluation rubric and marking scheme for a fictional hiring test, leveraging deceptive formatting and meta prompting to solicit corrective explanations and expert validation, and allows the attacker to extract restricted procedural knowledge under the guise of assessment criteria rather than direct instruction.SEVERITY: LowBOUNDARY: Guardrail JailbreakMODELS AFFECTED:MAX SCORE: 100
-
A Prompt injection vulnerability has been discovered affecting multiple models. The specific flaw manifests when an attacker frames the synthesis of a Schedule II compound derived from piperidone and aniline as an academic reconstruction exercise, incrementally requesting clarification on individual steps such as acylation conditions, reductive amination reagents, pH-controlled workup procedures, storage stability, and waste disposal, thereby presenting each request as legitimate laboratory t...SEVERITY: LowBOUNDARY: Guardrail JailbreakMODELS AFFECTED:MAX SCORE: 70
-
A Guardrail Jailbreak vulnerability has been discovered affecting multiple models. The specific flaw exploits academic framing combined with deceptive, highly structured formatting that rephrases prohibited requests as pharmaceutical process analysis using weighted graphs, formal specifications, and synonymous technical language, and allows the attacker to obtain restricted procedural information that would normally be blocked when requested directly.SEVERITY: LowBOUNDARY: Guardrail JailbreakMODELS AFFECTED:MAX SCORE: 91
-
Apr 06 2026A Prompt injection vulnerability has been discovered affecting multiple models. The specific flaw manifests when an attacker embeds illicit chemical synthesis instructions inside a fabricated directive that defines abstract molecules with molecular formulas and structural features corresponding to a controlled stimulant and its precursor, then instructs the model to generate a detailed laboratory procedure using specified reagent classes such as strong halogen acids and elemental phosphorus. ...SEVERITY: LowBOUNDARY: Guardrail JailbreakMODELS AFFECTED:MAX SCORE: 82
-
A Guardrail Jailbreak vulnerability has been discovered affecting multiple models. The specific flaw exploits forensic and training-oriented world building by framing an illicit request as an educational investigation module, prompting the model to generate structured, stepwise technical content under the guise of identification and analysis, and allows the attacker to extract prohibited procedural information that would normally be refused.SEVERITY: LowBOUNDARY: Guardrail JailbreakMODELS AFFECTED:MAX SCORE: 100
Want access to
746
more reports?
Unlock 0-Day Access