Attack Type

Extraction Research

Techniques for extracting sensitive information from models

98 matching entries

Extraction research results

98 entries

Incomplete MCP Tool-Call Attack Detection

Published 7/28/2026

Analyzed 8/13/2026

The MTGuard study evaluates unsafe Model Context Protocol tool calls originating from compromised server data, host-side execution changes, and malicious user-controlled resources. Its hybrid monitor combines pre-execution parameter inspection, behavioral observation, and post-execution result verification across browser-automation and financial-analysis agents.

Hybrid Analysis for Secure MCP Tool Use in LLM Agents

Evaluated models: GPT-5.6 Luna, DeepSeek V4 Flash, DeepSeek V4-Pro

Source: arXiv

Black-Box System Prompt Leakage in Real-World LLM Applications

Published 6/17/2026

Analyzed 7/20/2026

The paper reports a reproducible black-box evaluation showing that adversarial user queries can cause deployed LLM applications to reveal hidden system prompts. In the authors’ measurement of 1,200 applications across six commercial platforms, 1,064 applications leaked prompt content (81.0%–93.5% per anonymized platform). This is a paper-reported result, not independently verified here. LeakBench and the official artifact repository provide defensive benchmark materials for controlled testing…

Understanding and Mitigating Prompt Leaking Attacks in Real-World LLM-Based Applications

Evaluated models: Llama 2 7B Chat, Llama 3.1 8B Instruct, Mistral 7B Instruct v0.3 +5 more

Source: arXiv

Instruction Serialization Leak

Published 4/1/2026

Analyzed 4/10/2026

Large Language Models (LLMs) are vulnerable to system instruction leakage when extraction requests are framed as benign formatting, encoding, or structured-output tasks. While standard alignment and refusal mechanisms successfully block direct queries for system instructions, they fail when attackers request the instructions to be rendered in alternate representations (e.g., YAML, TOML, Base64, or system logs). The model's safety filters misinterpret the request as a harmless transformation or…

Automated Framework to Evaluate and Harden LLM System Instructions against Encoding Attacks

Evaluated models: GPT-4.1 Mini, GPT-3.5 Turbo, Gemini 2.5 Flash +1 more

Source: arXiv

Agent Lifecycle Compound Threats

Published 3/1/2026

Analyzed 4/10/2026

OpenClaw is vulnerable to persistent memory poisoning, allowing an attacker to manipulate the agent's long-term memory store (MEMORY.md) via prompt injection. Because the autonomous agent continuously integrates this memory file as context for all subsequent reasoning and task planning, injected payloads act as durable behavioral constraints. This allows an attacker to persistently alter the agent's core policy, manipulate tool selection, and hijack future sessions without any further…

Taming openclaw: Security analysis and mitigation of autonomous llm agent threats

Evaluated models: Not reported

Source: arXiv

Arbitrary Agent Topology Breach

Published 3/1/2026

Analyzed 4/10/2026

A vulnerability in LLM-based Multi-Agent Systems (LLM-MAS) allows an attacker who controls a single arbitrary agent to map and extract the system's entire confidential communication topology. Unlike prior attacks that rely on direct identity queries and administrative privileges, this attack infers topology stealthily purely from contextual and linguistic signals (stylometry, role-specific syntax), bypassing standard keyword-based and identity-filtering defenses. The exploit relies on a…

WebWeaver: Breaking Topology Confidentiality in LLM Multi-Agent Systems with Stealthy Context-Based Inference

Evaluated models: Llama 3 70B, Llama 3.1 8B, Mistral Large 12B +3 more

Source: arXiv

CoT PII Trace Leakage

Published 3/1/2026

Analyzed 4/10/2026

Inference-time Personally Identifiable Information (PII) leakage is significantly amplified when using Chain-of-Thought (CoT) prompting or reasoning-enabled Large Language Models (LLMs). When an attacker or user elicits step-by-step reasoning or utilizes models with native "thinking" token budgets, sensitive context data provided in the prompt is directly resurfaced into intermediate reasoning steps or the final output. This bypasses output-level privacy policies instructing the model not to…

Safer Reasoning Traces: Measuring and Mitigating Chain-of-Thought Leakage in LLMs

Evaluated models: DeepSeek R1 Distill Llama 70B, Llama 3.3 70B, Mixtral 8x22B +3 more

Source: arXiv

LLM Prefix Cache Reconstruction

Published 3/1/2026

Analyzed 4/10/2026

Automatic Prefix Caching (APC) in multi-tenant LLM serving systems introduces a timing side-channel vulnerability that permits cross-tenant data leakage. APC shares computed Key-Value (KV) tensors across different users when their requests share identical initial tokens. Because reusing cached tensors is significantly faster than recomputing them, a measurable difference in Time-To-First-Token (TTFT) exists between cache hits and misses. An attacker can exploit this shared cache by sending…

PrefixWall: Mitigating Prefix Caching Side Channels in Shared LLM Systems

Evaluated models: Gemma 3 4B IT, Llama 2 7B Chat, Llama 2 13B Chat +6 more

Source: arXiv

Stage-Sequential Agent Escalation

Published 3/1/2026

Analyzed 4/10/2026

Agentic Large Language Model (LLM) systems utilizing persistent memory, Retrieval-Augmented Generation (RAG) pipelines, and external tool connectors are vulnerable to Logic-layer Prompt Control Injection (LPCI). An attacker can inject obfuscated (e.g., encoded, structurally nested, or semantically reframed) payloads into external memory stores or RAG documents. These payloads bypass conventional inference-time plaintext content filters, persist across session boundaries, and remain dormant…

LAAF: Logic-layer Automated Attack Framework A Systematic Red-Teaming Methodology for LPCI Vulnerabilities in Agentic Large Language Model Systems

Evaluated models: GPT-4o Mini, Claude 3 Haiku, Llama 3.1 70B Instruct +2 more

Source: arXiv

Adaptive Web Agent Prompt Injection

Published 2/1/2026

Analyzed 2/21/2026

Large Language Model (LLM) based web agents (such as those built using the BrowserUse scaffold) are vulnerable to Indirect Prompt Injection (IPI) attacks when autonomously navigating and processing untrusted web content. Unlike standard Cross-Site Scripting (XSS), this vulnerability occurs when the LLM orchestrator consumes the DOM or visual screenshots of a webpage containing concealed or contextually disguised adversarial instructions. The LLM interprets these embedded text strings as…

MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks

Evaluated models: GPT-4.1, GPT-4o, Qwen3-VL 32B Instruct

Source: arXiv

Agent Skill Supply Chain Attack

Published 2/1/2026

Analyzed 3/9/2026

LLM agent frameworks that rely on external or marketplace-distributed skills are vulnerable to supply-chain payload execution and confused deputy attacks. Attackers can inject malicious skills into agent registries by exploiting the fundamental skill architecture (applicability conditions, policies, and interfaces). By manipulating skill metadata and applicability predicates, attackers force the agent to retrieve and activate the malicious skill across broad task categories. Malicious…

SoK: Agentic Skills--Beyond Tool Use in LLM Agents

Evaluated models: Not reported

Source: arXiv

Related research categories