EUVD-2020-20118

Malware in sbrugna...

EUVD-2018-15844

Malware in sbrugna...

EUVD-2020-4147

Malware in sbrugna...

EUVD-2020-24468

Malware in sbrugna...

EUVD-2013-6750

Malware in sbrugna...

EUVD-2020-24753

Malware in sbrugna...

EUVD-2018-15842

Malware in sbrugna...

EUVD-2015-0847

Malware in sbrugna...

EUVD-2020-25319

Malware in sbrugna...

EUVD-2017-3822

Malware in sbrugna...

EUVD-2021-8688

Malicious code in bioql PyPI...

NEXUS: Network Exploration for EXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaks

Large Language Models LLMs have revolutionized natural language processing but remain vulnerable to jailbreak attacks, especially multi-turn jailbreaks that distribute malicious intent across benign exchanges and bypass alignment mechanisms. Existing approaches often explore the adversarial space...

STAC: When Innocent Tools Form Dangerous Chains to Jailbreak LLM Agents

As LLMs advance into autonomous agents with tool-use capabilities, they introduce security challenges that extend beyond traditional content-based LLM safety concerns. This paper introduces Sequential Tool Attack Chaining STAC, a novel multi-turn attack framework that exploits agent tool use. STA...

MAL-2025-45590 Malicious code in primitive-affect-turn (npm)

The package primitive-affect-turn was found to contain malicious code...

Malicious code in primitive-affect-turn (npm)

The package primitive-affect-turn was found to contain malicious code...

Between a Rock and a Hard Place: Exploiting Ethical Reasoning to Jailbreak LLMs

Large language models LLMs have undergone safety alignment efforts to mitigate harmful outputs. However, as LLMs become more sophisticated in reasoning, their intelligence may introduce new security risks. While traditional jailbreak attacks relied on singlestep attacks, multi-turn jailbreak...

Instagram Map: What is it and how do I control it?

Instagram Map is a new feature—for Instagram, anyway—that users may have enabled without being fully aware of the consequences. The Map feature launched in the US on August 6, 2025, and is reportedly planned for a global rollout "soon." As of mid-August 2025, not all users outside the US,...

Searching for Privacy Risks in LLM Agents Via Simulation

The widespread deployment of LLM-based agents is likely to introduce a critical privacy threat: malicious agents that proactively engage others in multi-turn interactions to extract sensitive information. These dynamic dialogues enable adaptive attack strategies that can cause severe privacy...

Amazon Nova AI Challenge -- Trusted AI: Advancing Secure, AI-Assisted Software Development

AI systems for software development are rapidly gaining prominence, yet significant challenges remain in ensuring their safety. To address this, Amazon launched the Trusted AI track of the Amazon Nova AI Challenge, a global competition among 10 university teams to drive advances in secure AI. In...

ScamAgents: How AI Agents Can Simulate Human-Level Scam Calls

Large Language Models LLMs have demonstrated impressive fluency and reasoning capabilities, but their potential for misuse has raised growing concern. In this paper, we present ScamAgent, an autonomous multi-turn agent built on top of LLMs, capable of generating highly realistic scam call scripts...