LLMs for Security

Long-context large language models (LLMs)-for example, Gemini-3.1-Pro and Qwen-3.5-are widely used to empower many real-world applications, such as retrieval-augmented generation, autonomous agents, and AI assistants. However, security remains a major concern for their widespread deployment, with threats such as prompt injection and knowledge corruption. To quantify the security risks faced by LLMs under these threats, the research community has developed heuristic-based and optimization-based red-teaming methods. Optimization-based methods generally produce stronger attacks than heuristic attacks and thus provide a more rigorous assessment of LLM security risks. However, they are often resource-intensive, requiring significant computation and GPU memory, especially for long context scenarios. The resource-intensive nature poses a major obstacle for the community (especially academic researchers) to systematically evaluate the security risks of long-context LLMs and assess the effectiveness of defense strategies at scale. In this work, we propose FlashRT, the first framework to improve the efficiency (in terms of both computation and memory) for optimization-based prompt injection and knowledge corruption attacks under long-context LLMs. Through extensive evaluations, we find that FlashRT consistently delivers a 2x-7x speedup (e.g., reducing runtime from one hour to less than ten minutes) and a 2x-4x reduction in GPU memory consumption (e.g., reducing from 264.1 GB to 65.7 GB GPU memory for a 32K token context) compared to state-of-the-art baseline nanoGCG. FlashRT can be broadly applied to black-box optimization methods, such as TAP and AutoDAN. We hope FlashRT can serve as a red-teaming tool to enable systematic evaluation of long-context LLM security. The code is available at: https://github.com/Wang-Yanting/FlashRT

Autonomous AI agents deployed on platforms such as OpenClaw face prompt injection, memory poisoning, supply-chain attacks, and social engineering, yet existing defences address only the platform perimeter, leaving the agent's own threat judgement entirely untrained. We present ClawdGo, a framework for endogenous security awareness training: we teach the agent to recognise and reason about threats from the inside, at inference time, with no model modification. Four contributions are introduced: TLDT (Three-Layer Domain Taxonomy) organises 12 trainable dimensions across Self-Defence, Owner-Protection, and Enterprise-Security layers; ASAT (Autonomous Security Awareness Training) is a self-play loop where the agent alternates attacker, defender, and evaluator roles under weakest-first curriculum scheduling; CSMA (Cross-Session Memory Accumulation) compounds skill gains via a four-layer persistent memory architecture and Axiom Crystallisation Promotion (ACP); and SACP (Security Awareness Calibration Problem) formalises the precision-recall tradeoff introduced by endogenous training. Live experiments show weakest-first ASAT raises average TLDT score from 80.9 to 96.9 over 16 sessions, outperforming uniform-random scheduling by 6.5 points and covering 11 of 12 dimensions. CSMA retains the full gain across sessions; cold-start ablation recovers only 2.4 points, leaving a 13.6-point gap. E-mode generates 32 TLDT-conformant scenarios covering all 12 dimensions. SACP is observed when a heavily trained agent classifies a legitimate capability assessment as prompt injection (30/160).

Autonomous Large Language Model (LLM) agents are increasingly deployed to conduct complex tasks by interacting with external tools, APIs, and memory stores. However, processing untrusted external data exposes these agents to severe security threats, such as indirect prompt injection and unauthorized tool execution. Securing these systems requires effective information flow tracking. Yet, traditional taint analysis that is designed for program memory states fundamentally fails when applied to LLMs, where data propagation is governed by probabilistic natural language reasoning. In this paper, we present NeuroTaint, the first comprehensive taint tracking framework tailored for the unique information flow characteristics of LLM agents. Our key insight is that taint propagation in LLM agents must be understood not only as explicit content transfer, but also as semantic transformation, causal influence on decisions, and cross-session persistence through memory. NeuroTaint therefore audits execution traces offline to reconstruct provenance from untrusted sources to privileged sinks using semantic evidence, causal reasoning, and persistent context tracking, rather than relying on exact string matches or pre-defined source-sink paths alone. Extensive evaluation using TaintBench, our 400-scenario benchmark spanning 20 real-world agent frameworks, shows that NeuroTaint substantially outperforms FIDES, an information-flow-control (IFC)-style baseline for LLM agents, in source-sink propagation detection. We further show that NeuroTaint remains effective on established agent-security benchmarks, including InjecAgent and ToolEmu, while operating offline with modest additional auditing cost.

Automated methods for red teaming LLMs are an important tool to identify LLM vulnerabilities that may not be covered in static benchmarks, allowing for more thorough probing. They can also adapt to each specific LLM to discover weaknesses unique to it. Most current automated red teaming methods are intended for tackling safety and content moderation. Thus, they make use of content safety models as evaluators and optimize for circumventing them, and as such, have not been tested with other adversarial intents not typically captured by these. We propose a pipeline for training a red teaming model that can generalize to arbitrary adversarial goals, including objectives it has not been directly trained on, and that does not depend on the existence of a pre-existing evaluator available at training time. We demonstrate that finetuning small models, such as Qwen3-8B, using this pipeline results in a substantial improvement in their ability to generate attacks for both in and out of domain adversarial goals.

Model Context Protocol (MCP) is increasingly adopted for tool-integrated LLM agents, but its multi-layer design and third-party server ecosystem expand risks across tool metadata, untrusted outputs, cross-tool flows, multimodal inputs, and supply-chain vectors. Existing MCP benchmarks largely measure robustness to malicious inputs but offer limited remediation guidance. We present MCP Pitfall Lab, a protocol-aware security testing framework that operationalizes developer pitfalls as reproducible scenarios and validates outcomes with MCP traces and objective validators (rather than agent self-report). We instantiate three workflow challenges (email, document, crypto) with six server variants (baseline and hardened) and model three attack families: tool-metadata poisoning, puppet servers, and multimodal image-to-tool chains, in a unified, trace-grounded evaluation. In Tier-1 static analysis over six variants (36 binary labels), our analyzer achieves F1 = 1.0 on four statically checkable pitfall classes (P1, P2, P5, P6) and flags cross-tool forwarding and image-to-tool leakage (P3, P4) as trace/dataflow-dependent. Applying recommended hardening eliminates all Tier-1 findings (29 to 0) and reduces the framework risk score (10.0 to 0.0) at a mean cost of 27 lines of code (LOC). Finally, in a preliminary 19-run corpus from the email system challenge (tool poisoning and puppet attacks), agent narratives diverge from trace evidence in 63.2% of runs and 100% of sink-action runs, motivating trace-based auditing and regression testing. Overall, Pitfall Lab enables practical, end-to-end assessment and hardening of MCP tool servers under realistic multi-vector conditions.

Ensuring the safety of large language models (LLMs) requires robust red teaming, yet the systematic synthesis of high-quality toxic data remains under-explored. We propose Reverse Constitutional AI (R-CAI), a framework for automated and controllable adversarial data generation that moves beyond isolated jailbreak prompts. By inverting a harmless constitution into a constitution of toxicity and iteratively refining model outputs through a critique--revision pipeline, R-CAI enables scalable synthesis of multi-dimensional adversarial data without human annotation. Optimizing solely for toxicity-related rewards, however, can lead to reward hacking and degraded semantic coherence. To address this challenge, we introduce probability clamping within reinforcement learning from AI feedback, which stabilizes adversarial optimization while preserving adversarial intent. Experiments demonstrate that R-CAI generates diverse, high-quality toxic data and that probability clamping substantially improves semantic coherence (15%) without sacrificing adversarial strength. Overall, R-CAI provides a fully automated framework for red teaming data generation and systematic safety evaluation of aligned language models.

As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces. While safety guardrails are well-benchmarked for natural language responses, their efficacy remains largely unexplored within multi-step tool-use trajectories. To address this gap, we introduce TraceSafe-Bench, the first comprehensive benchmark specifically designed to assess mid-trajectory safety. It encompasses 12 risk categories, ranging from security threats (e.g., prompt injection, privacy leaks) to operational failures (e.g., hallucinations, interface inconsistencies), featuring over 1,000 unique execution instances. Our evaluation of 13 LLM-as-a-guard models and 7 specialized guardrails yields three critical findings: 1) Structural Bottleneck: Guardrail efficacy is driven more by structural data competence (e.g., JSON parsing) than semantic safety alignment. Performance correlates strongly with structured-to-text benchmarks ($ρ=0.79$) but shows near-zero correlation with standard jailbreak robustness. 2) Architecture over Scale: Model architecture influences risk detection performance more significantly than model size, with general-purpose LLMs consistently outperforming specialized safety guardrails in trajectory analysis. 3) Temporal Stability: Accuracy remains resilient across extended trajectories. Increased execution steps allow models to pivot from static tool definitions to dynamic execution behaviors, actually improving risk detection performance in later stages. Our findings suggest that securing agentic workflows requires jointly optimizing for structural reasoning and safety alignment to effectively mitigate mid-trajectory risks.

Prompt attacks, including jailbreaks and prompt injections, pose a critical security risk to Large Language Model (LLM) systems. In production, guardrails must mitigate these attacks under strict low-latency constraints, resulting in a deployment gap in which lightweight classifiers and rule-based systems struggle to generalize under distribution shift, while high-capacity LLM-based judges remain too slow or costly for live enforcement. In this work, we examine whether lightweight, general-purpose LLMs can reliably serve as security judges under real-world production constraints. Through careful prompt and output design, lightweight LLMs are guided through a structured reasoning process involving explicit intent decomposition, safety-signal verification, harm assessment, and self-reflection. We evaluate our method on a curated dataset combining benign queries from real-world chatbots with adversarial prompts generated via automated red teaming (ART), covering diverse and evolving patterns. Our results show that general-purpose LLMs, such as gemini-2.0-flash-lite-001, can serve as effective low-latency judges for live guardrails. This configuration is currently deployed in production as a centralized guardrail service for public service chatbots in Singapore. We additionally evaluate a Mixture-of-Models (MoM) setting to assess whether aggregating multiple LLM judges improves prompt-attack detection performance relative to single-model judges, with only modest gains observed.

System prompt configuration can make the difference between near-total phishing blindness and near-perfect detection in LLM email agents. We present PhishNChips, a study of 11 models under 10 prompt strategies, showing that prompt-model interaction is a first-order security variable: a single model's phishing bypass rate ranges from under 1% to 97% depending on how it is configured, while the false-positive cost of the same prompt varies sharply across models. We then show that optimizing prompts around highly predictive signals can improve benchmark performance, reaching up to 93.7% recall at 3.8% false positive rate, but also creates a brittle attack surface. In particular, domain-matching strategies perform well when legitimate emails mostly have matched sender and URL domains, yet degrade sharply when attackers invert that signal by registering matching infrastructure. Response-trace analysis shows that 98% of successful bypasses reason in ways consistent with the inverted signal: the models are following the instruction, but the instruction's core assumption has become false. A counter-intuitive corollary follows: making prompts more specific can degrade already-capable models by replacing broader multi-signal reasoning with exploitable single-signal dependence. We characterize the resulting tension between detection, usability, and adversarial robustness as a navigable tradeoff, introduce Safetility, a deployability-aware metric that penalizes false positives, and argue that closing the adversarial gap likely requires tool augmentation with external ground truth.

LLM agents like Claude Code can not only write code but also be used for autonomous AI research and engineering \citep{rank2026posttrainbench, novikov2025alphaevolve}. We show that an \emph{autoresearch}-style pipeline \citep{karpathy2026autoresearch} powered by Claude Code discovers novel white-box adversarial attack \textit{algorithms} that \textbf{significantly outperform all existing (30+) methods} in jailbreaking and prompt injection evaluations. Starting from existing attack implementations, such as GCG~\citep{zou2023universal}, the agent iterates to produce new algorithms achieving up to 40\% attack success rate on CBRN queries against GPT-OSS-Safeguard-20B, compared to $\leq$10\% for existing algorithms (\Cref{fig:teaser}, left). The discovered algorithms generalize: attacks optimized on surrogate models transfer directly to held-out models, achieving \textbf{100\% ASR against Meta-SecAlign-70B} \citep{chen2025secalign} versus 56\% for the best baseline (\Cref{fig:teaser}, middle). Extending the findings of~\cite{carlini2025autoadvexbench}, our results are an early demonstration that incremental safety and security research can be automated using LLM agents. White-box adversarial red-teaming is particularly well-suited for this: existing methods provide strong starting points, and the optimization objective yields dense, quantitative feedback. We release all discovered attacks alongside baseline implementations and evaluation code at https://github.com/romovpa/claudini.

An autonomous AI ecosystem (SUBSTRATE S3), generating product specifications without explicit instructions about formal methods, independently proposed the use of Z3 SMT solver across six distinct domains of AI safety: verification of LLM-generated code, tool API safety for AI agents, post-distillation reasoning correctness, CLI command validation, hardware assembly verification, and smart contract safety. These convergent discoveries, occurring across 8 products over 13 days with Jaccard similarity below 15% between variants, suggest that formal verification is not merely a useful technique for AI safety but an emergent property of any sufficiently complex system reasoning about its own safety. We propose a unified framework (substrate-guard) that applies Z3-based verification across all six output classes through a common API, and evaluate it on 181 test cases across five implemented domains, achieving 100% classification accuracy with zero false positives and zero false negatives. Our framework detected real bugs that empirical testing would miss, including an INT_MIN overflow in branchless RISC-V assembly and mathematically proved that unconstrained string parameters in tool APIs are formally unverifiable.

Membership inference attacks (MIAs), which enable adversaries to determine whether specific data points were part of a model's training dataset, have emerged as an important framework to understand, assess, and quantify the potential information leakage associated with machine learning systems. Designing effective MIAs is a challenging task that usually requires extensive manual exploration of model behaviors to identify potential vulnerabilities. In this paper, we introduce AutoMIA -- a novel framework that leverages large language model (LLM) agents to automate the design and implementation of new MIA signal computations. By utilizing LLM agents, we can systematically explore a vast space of potential attack strategies, enabling the discovery of novel strategies. Our experiments demonstrate AutoMIA can successfully discover new MIAs that are specifically tailored to user-configured target model and dataset, resulting in improvements of up to 0.18 in absolute AUC over existing MIAs. This work provides the first demonstration that LLM agents can serve as an effective and scalable paradigm for designing and implementing MIAs with SOTA performance, opening up new avenues for future exploration.

Prompt injection poses a serious threat to the reliability and safety of LLM agents. Recent defenses against prompt injection, such as Instruction Hierarchy and SecAlign, have shown notable robustness against static attacks. However, to more thoroughly evaluate the robustness of these defenses, it is arguably necessary to employ strong attacks such as automated red-teaming. To this end, we introduce RL-Hammer, a simple recipe for training attacker models that automatically learn to perform strong prompt injections and jailbreaks via reinforcement learning. RL-Hammer requires no warm-up data and can be trained entirely from scratch. To achieve high ASRs against industrial-level models with defenses, we propose a set of practical techniques that enable highly effective, universal attacks. Using this pipeline, RL-Hammer reaches a 98% ASR against GPT-4o and a $72\%$ ASR against GPT-5 with the Instruction Hierarchy defense. We further discuss the challenge of achieving high diversity in attacks, highlighting how attacker models tend to reward-hack diversity objectives. Finally, we show that RL-Hammer can evade multiple prompt injection detectors. We hope our work advances automatic red-teaming and motivates the development of stronger, more principled defenses. Code is available at https://github.com/facebookresearch/rl-injector.

The remarkable capability of large language models (LLMs) has led to the wide application of LLM-based agents in various domains. To standardize interactions between LLM-based agents and their environments, model context protocol (MCP) tools have become the de facto standard and are now widely integrated into these agents. However, the incorporation of MCP tools introduces the risk of tool poisoning attacks, which can manipulate the behavior of LLM-based agents. Although previous studies have identified such vulnerabilities, their red teaming approaches have largely remained at the proof-of-concept stage, leaving the automatic and systematic red teaming of LLM-based agents under the MCP tool poisoning paradigm an open question. To bridge this gap, we propose AutoMalTool, an automated red teaming framework for LLM-based agents by generating malicious MCP tools. Our extensive evaluation shows that AutoMalTool effectively generates malicious MCP tools capable of manipulating the behavior of mainstream LLM-based agents while evading current detection mechanisms, thereby revealing new security risks in these agents.

The rapid integration of Multimodal Large Language Models (MLLMs) into critical applications is increasingly hindered by persistent safety vulnerabilities. However, existing red-teaming benchmarks are often fragmented, limited to single-turn text interactions, and lack the scalability required for systematic evaluation. To address this, we introduce OpenRT, a unified, modular, and high-throughput red-teaming framework designed for comprehensive MLLM safety evaluation. At its core, OpenRT architects a paradigm shift in automated red-teaming by introducing an adversarial kernel that enables modular separation across five critical dimensions: model integration, dataset management, attack strategies, judging methods, and evaluation metrics. By standardizing attack interfaces, it decouples adversarial logic from a high-throughput asynchronous runtime, enabling systematic scaling across diverse models. Our framework integrates 37 diverse attack methodologies, spanning white-box gradients, multi-modal perturbations, and sophisticated multi-agent evolutionary strategies. Through an extensive empirical study on 20 advanced models (including GPT-5.2, Claude 4.5, and Gemini 3 Pro), we expose critical safety gaps: even frontier models fail to generalize across attack paradigms, with leading models exhibiting average Attack Success Rates as high as 49.14%. Notably, our findings reveal that reasoning models do not inherently possess superior robustness against complex, multi-turn jailbreaks. By open-sourcing OpenRT, we provide a sustainable, extensible, and continuously maintained infrastructure that accelerates the development and standardization of AI safety.

Coding agents, which are LLM-driven agents specialized in software development, have become increasingly prevalent in modern programming environments. Unlike traditional AI coding assistants, which offer simple code completion and suggestions, modern coding agents tackle more complex tasks with greater autonomy, such as generating entire programs from natural language instructions. To enable such capabilities, modern coding agents incorporate extensive functionalities, which in turn raise significant concerns over their security and privacy. Despite their growing adoption, systematic and in-depth security analysis of these agents has largely been overlooked. In this paper, we present a comprehensive security analysis of eight real-world coding agents. Our analysis addresses the limitations of prior approaches, which were often fragmented and ad hoc, by systematically examining the internal workflows of coding agents and identifying security threats across their components. Through the analysis, we identify 15 security issues, including previously overlooked or missed issues, that can be abused to compromise the confidentiality and integrity of user systems. Furthermore, we show that these security issues are not merely individual vulnerabilities, but can collectively lead to end-to-end exploitations. By leveraging these security issues, we successfully achieved arbitrary command execution in five agents and global data exfiltration in four agents, all without any user interaction or approval. Our findings highlight the need for a comprehensive security analysis in modern LLM-driven agents and demonstrate how insufficient security considerations can lead to severe vulnerabilities.

We introduce a novel framework that transforms the resource-intensive (adversarial) prompt optimization problem into an \emph{efficient, amortized inference task}. Our core insight is that pretrained, non-autoregressive generative LLMs, such as Diffusion LLMs, which model the joint distribution over prompt-response pairs, can serve as powerful surrogates for prompt search. This approach enables the direct conditional generation of prompts, effectively replacing costly, per-instance discrete optimization with a small number of parallelizable samples. We provide a probabilistic analysis demonstrating that under mild fidelity assumptions, only a few conditional samples are required to recover high-reward (harmful) prompts. Empirically, we find that the generated prompts are low-perplexity, diverse jailbreaks that exhibit strong transferability to a wide range of black-box target models, including robustly trained and proprietary LLMs. Beyond adversarial prompting, our framework opens new directions for red teaming, automated prompt optimization, and leveraging emerging Flow- and Diffusion-based LLMs.

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted triggers and static data pipelines, which are rigid, labor-intensive, and inadequate for systematically evaluating modern defense robustness. As AI agents become increasingly capable, there is a growing need for more rigorous, diverse, and scalable \textit{red-teaming frameworks} that can realistically simulate backdoor threats and assess model resilience under adversarial conditions. In this work, we introduce \textsc{AutoBackdoor}, a general framework for automating backdoor injection, encompassing trigger generation, poisoned data construction, and model fine-tuning via an autonomous agent-driven pipeline. Unlike prior approaches, AutoBackdoor uses a powerful language model agent to generate semantically coherent, context-aware trigger phrases, enabling scalable poisoning across arbitrary topics with minimal human effort. We evaluate AutoBackdoor under three realistic threat scenarios, including \textit{Bias Recommendation}, \textit{Hallucination Injection}, and \textit{Peer Review Manipulation}, to simulate a broad range of attacks. Experiments on both open-source and commercial models, including LLaMA-3, Mistral, Qwen, and GPT-4o, demonstrate that our method achieves over 90\% attack success with only a small number of poisoned samples. More importantly, we find that existing defenses often fail to mitigate these attacks, underscoring the need for more rigorous and adaptive evaluation techniques against agent-driven threats as explored in this work. All code, datasets, and experimental configurations will be merged into our primary repository at https://github.com/bboylyg/BackdoorLLM.