844 matches found
OpenAI’s Guardrails Can Be Bypassed by Simple Prompt Injection Attack
Just weeks after its release, OpenAI’s Guardrails system was quickly bypassed by researchers. Read how simple prompt injection attacks fooled the system’s AI judges and exposed an ongoing security concern for OpenAI...
AI Pulse: OpenAI’s Wild Bot Behavior After GPT-5
The AI Pulse series breaks down traffic trends and what they mean for apps, APIs, and businesses. In this post, read how OpenAI’s bots are changing after GPT-5...
GHSA-6FVQ-23CW-5628 vLLM: Resource-Exhaustion (DoS) through Malicious Jinja Template in OpenAI-Compatible Server
Summary A resource-exhaustion denial-of-service vulnerability exists in multiple endpoints of the OpenAI-Compatible Server due to the ability to specify Jinja templates via the chattemplate and chattemplatekwargs parameters. If an attacker can supply these parameters to the API, they can cause a...
EUVD-2025-23957
Malicious code in bioql PyPI...
EUVD-2025-6631
Malicious code in bioql PyPI...
EUVD-2024-16248
Malicious code in bioql PyPI...
EUVD-2025-6656
Malicious code in bioql PyPI...
EUVD-2024-16246
Malicious code in bioql PyPI...
EUVD-2025-7048
Malicious code in bioql PyPI...
EUVD-2025-9187
Malicious code in bioql PyPI...
EUVD-2025-6651
Malicious code in bioql PyPI...
EUVD-2024-53177
Malicious code in bioql PyPI...
EUVD-2025-22560
Malicious code in bioql PyPI...
EUVD-2025-7002
Malicious code in bioql PyPI...
EUVD-2024-44436
Malicious code in bioql PyPI...
EUVD-2024-45879
Malicious code in bioql PyPI...
EUVD-2024-38530
Malicious code in bioql PyPI...
EUVD-2025-6939
Malicious code in bioql PyPI...