6 papers
When the Defense Writes the Refusal: Auditing Keyword-Scored Evaluation of Inference-Time Defenses for Multimodal Large Language Models
Bulat Nutfullin, Vladimir Evgrafov, Dmitry Namiot
The paper audits the evaluation of inference-time safety defenses for multimodal large language models, revealing provenance and implementation errors in benchmark pipelines and pr…
Sleeper Channels and Provenance Gates: Persistent Prompt Injection in Always-on Autonomous AI Agents
Narek Maloyan, Dmitry Namiot
Always-on AI agents (OpenClaw, Hermes Agent) run as a single persistent process under the owner's identity, folding messaging, memory, self-authored skills, scheduling, and shell i…
Breaking the Protocol: Security Analysis of the Model Context Protocol Specification and Prompt Injection Vulnerabilities in Tool-Integrated LLM Agents
Narek Maloyan, Dmitry Namiot
The Model Context Protocol (MCP) has emerged as a de facto standard for integrating Large Language Models with external tools, yet no formal security analysis of the protocol speci…
Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems
Narek Maloyan, Dmitry Namiot
The proliferation of agentic AI coding assistants, including Claude Code, GitHub Copilot, Cursor, and emerging skill-based architectures, has fundamentally transformed software dev…
Investigating the Vulnerability of LLM-as-a-Judge Architectures to Prompt-Injection Attacks
Narek Maloyan, Bislan Ashinov, Dmitry Namiot
Large Language Models (LLMs) are increasingly employed as evaluators (LLM-as-a-Judge) for assessing the quality of machine-generated text. This paradigm offers scalability and cost…
Adversarial Attacks on LLM-as-a-Judge Systems: Insights from Prompt Injections
Narek Maloyan, Dmitry Namiot
LLM as judge systems used to assess text quality code correctness and argument strength are vulnerable to prompt injection attacks. We introduce a framework that separates content…