Related papers: Owner-Harm: A Missing Threat Model for AI Agent Sa…
Evolving AI systems increasingly deploy multi-agent architectures where autonomous agents collaborate, share information, and delegate tasks through developing protocols. This connectivity, while powerful, introduces novel security risks.…
The rapid diffusion of agentic AI has created a new coverage problem for commercial insurance: some AI-mediated losses are now affirmatively insured, some create silent-AI exposure under legacy cyber, technology errors-and-omissions (E&O),…
Recent improvement gains in large language models (LLMs) have lead to everyday usage of AI-based Conversational Agents (CAs). At the same time, LLMs are vulnerable to an array of threats, including jailbreaks and, for example, causing…
Generative AI agents, software systems powered by Large Language Models (LLMs), are emerging as a promising approach to automate cybersecurity tasks. Among the others, penetration testing is a challenging field due to the task complexity…
Healthcare AI systems face major vulnerabilities to data poisoning that current defenses and regulations cannot adequately address. We analyzed eight attack scenarios in four categories: architectural attacks on convolutional neural…
Agent Skills is an emerging open standard that defines a modular, filesystem-based packaging format enabling LLM-based agents to acquire domain-specific expertise on demand. Despite rapid adoption across multiple agentic platforms and the…
We define Oracle Poisoning, an attack class in which an adversary corrupts a structured knowledge graph that AI agents query at runtime via tool-use protocols, causing incorrect conclusions through correct reasoning. Unlike prompt…
Agentic frameworks are the software layer through which AI agents act in the world. Existing safety methods intervene on the model and therefore remain conditional on unverifiable properties of learned behavior. We introduce containment…
Autonomous agents powered by large language models introduce a class of execution-layer vulnerabilities -- prompt injection, retrieval poisoning, and uncontrolled tool invocation -- that existing guardrails fail to address systematically.…
Recent proposals advocate using keystroke timing signals, specifically the coefficient of variation ($\delta$) of inter-keystroke intervals, to distinguish human-composed text from AI-generated content. We demonstrate that this class of…
The generalization capabilities of Large Language Models (LLMs) have led to their widespread deployment across various applications. However, this increased adoption has introduced several security threats, notably in the forms of…
Tool-augmented AI agents substantially extend the practical capabilities of large language models, but they also introduce security risks that cannot be identified through model-only evaluation. In this paper, we present a systematic…
Autonomous agent frameworks built upon large language models (LLMs) are evolving into complex, tool-integrated, and continuously operating systems, introducing security risks beyond traditional prompt-level vulnerabilities. As this paradigm…
Various AI safety datasets have been developed to measure LLMs against evolving interpretations of harm. Our evaluation of five recently published open-source safety benchmarks reveals distinct semantic clusters using UMAP dimensionality…
Large Language Models (LLMs) based autonomous agents demonstrate multifaceted capabilities to contribute substantially to economic production. However, existing benchmarks remain focused on single agentic capability, failing to capture…
The increasing adoption of LLM agents with access to numerous tools and sensitive data significantly widens the attack surface for indirect prompt injections. Due to the context-dependent nature of attacks, however, current defenses are…
As AI agents transition from research prototypes to enterprise production systems, the tool interfaces they consume remain rooted in human-oriented CRUD paradigms. This paper identifies five fundamental architectural mismatches between…
Agent ecosystems increasingly rely on installable skills to extend functionality, and some skills bundle learned model artifacts as part of their execution logic. This creates a supply-chain risk that is not captured by prompt injection or…
With the rise of personalized, persistent LLM agent frameworks such as OpenClaw, human-centered agentic social networks in which teams of collaborative AI agents serve individual users in a social network across multiple domains are…
As vendors adopt AI technologies, security researchers are working to uncover and fix related vulnerabilities, which is important given AI systems handle sensitive data and critical functions. This process relies on vendors receiving and…