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.

Agentic AI has been a topic of great interest recently. A Large Language Model (LLM) agent involves one or more LLMs in the back-end. In the front end, it conducts autonomous decision-making by combining the LLM outputs with results obtained by invoking several external tools. The autonomous interactions with the external environment introduce critical security risks. In this paper, we present a grey-box approach to explore diverse behaviors and uncover security risks in LLM agents. Our approach VeriGrey uses the sequence of tools invoked as a feedback function to drive the testing process. This helps uncover infrequent but dangerous tool invocations that cause unexpected agent behavior. As mutation operators in the testing process, we mutate prompts to design pernicious injection prompts. This is carefully accomplished by linking the task of the agent to an injection task, so that the injection task becomes a necessary step of completing the agent functionality. Comparing our approach with a black-box baseline on the well-known AgentDojo benchmark, VeriGrey achieves 33% additional efficacy in finding indirect prompt injection vulnerabilities with a GPT-4.1 back-end. We also conduct real-world case studies with the widely used coding agent Gemini CLI, and the well-known OpenClaw personal assistant. VeriGrey finds prompts inducing several attack scenarios that could not be identified by black-box approaches. In OpenClaw, by constructing a conversation agent which employs mutational fuzz testing as needed, VeriGrey is able to discover malicious skill variants from 10 malicious skills (with 10/10= 100% success rate on the Kimi-K2.5 LLM backend, and 9/10= 90% success rate on Opus 4.6 LLM backend). This demonstrates the value of a dynamic approach like VeriGrey to test agents, and to eventually lead to an agent assurance framework.

Autonomous AI agents powered by large language models are being deployed in production with capabilities including shell execution, file system access, database queries, and multi-party communication. Recent red teaming research demonstrates that these agents exhibit critical vulnerabilities in realistic settings: unauthorized compliance with non-owner instructions, sensitive information disclosure, identity spoofing, cross-agent propagation of unsafe practices, and indirect prompt injection through external resources [7]. In healthcare environments processing Protected Health Information, every such vulnerability becomes a potential HIPAA violation. This paper presents a security architecture deployed for nine autonomous AI agents in production at a healthcare technology company. We develop a six-domain threat model for agentic AI in healthcare covering credential exposure, execution capability abuse, network egress exfiltration, prompt integrity failures, database access risks, and fleet configuration drift. We implement four-layer defense in depth: (1) kernel level workload isolation using gVisor on Kubernetes, (2) credential proxy sidecars preventing agent containers from accessing raw secrets, (3) network egress policies restricting each agent to allowlisted destinations, and (4) a prompt integrity framework with structured metadata envelopes and untrusted content labeling. We report results from 90 days of deployment including four HIGH severity findings discovered and remediated by an automated security audit agent, progressive fleet hardening across three VM image generations, and defense coverage mapped to all eleven attack patterns from recent literature. All configurations, audit tooling, and the prompt integrity framework are released as open source.

Automated LLM vulnerability scanners are increasingly used to assess security risks by measuring different attack type success rates (ASR). Yet the validity of these measurements hinges on an often-overlooked component: the evaluator who determines whether an attack has succeeded. In this study, we demonstrate that commonly used open-source scanners exhibit measurement instability that depends on the evaluator component. Consequently, changing the evaluator while keeping the attacks and model outputs constant can significantly alter the reported ASR. To tackle this problem, we present a two-phase, reliability-aware evaluation framework. In the first phase, we quantify evaluator disagreement to identify attack categories where ASR reliability cannot be assumed. In the second phase, we propose a verification-based evaluation method where evaluators are validated by an independent verifier, enabling reliability assessment without relying on extensive human annotation. Applied to the widely used Garak scanner, we observe that 22 of 25 attack categories exhibit evaluator instability, reflected in high disagreement among evaluators. Our approach raises evaluator accuracy from 72% to 89% while enabling selective deployment to control cost and computational overhead. We further quantify evaluator uncertainty in ASR estimates, showing that reported vulnerability scores can vary by up to 33% depending on the evaluator. Our results indicate that the outputs of vulnerability scanners are highly sensitive to the choice of evaluators. Our framework offers a practical approach to quantify unreliable evaluations and enhance the reliability of measurements in automated LLM security assessments.

Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents. Although many defenses have been proposed, their robustness against adaptive attacks remains insufficiently evaluated, potentially creating a false sense of security. In this work, we propose PISmith, a reinforcement learning (RL)-based red-teaming framework that systematically assesses existing prompt-injection defenses by training an attack LLM to optimize injected prompts in a practical black-box setting, where the attacker can only query the defended LLM and observe its outputs. We find that directly applying standard GRPO to attack strong defenses leads to sub-optimal performance due to extreme reward sparsity -- most generated injected prompts are blocked by the defense, causing the policy's entropy to collapse before discovering effective attack strategies, while the rare successes cannot be learned effectively. In response, we introduce adaptive entropy regularization and dynamic advantage weighting to sustain exploration and amplify learning from scarce successes. Extensive evaluation on 13 benchmarks demonstrates that state-of-the-art prompt injection defenses remain vulnerable to adaptive attacks. We also compare PISmith with 7 baselines across static, search-based, and RL-based attack categories, showing that PISmith consistently achieves the highest attack success rates. Furthermore, PISmith achieves strong performance in agentic settings on InjecAgent and AgentDojo against both open-source and closed-source LLMs (e.g., GPT-4o-mini and GPT-5-nano). Our code is available at https://github.com/albert-y1n/PISmith.

The rapid adoption of large language models (LLMs) in financial services introduces new operational, regulatory, and security risks. Yet most red-teaming benchmarks remain domain-agnostic and fail to capture failure modes specific to regulated BFSI settings, where harmful behavior can be elicited through legally or professionally plausible framing. We propose a risk-aware evaluation framework for LLM security failures in Banking, Financial Services, and Insurance (BFSI), combining a domain-specific taxonomy of financial harms, an automated multi-round red-teaming pipeline, and an ensemble-based judging protocol. We introduce the Risk-Adjusted Harm Score (RAHS), a risk-sensitive metric that goes beyond success rates by quantifying the operational severity of disclosures, accounting for mitigation signals, and leveraging inter-judge agreement. Across diverse models, we find that higher decoding stochasticity and sustained adaptive interaction not only increase jailbreak success, but also drive systematic escalation toward more severe and operationally actionable financial disclosures. These results expose limitations of single-turn, domain-agnostic security evaluation and motivate risk-sensitive assessment under prolonged adversarial pressure for real-world BFSI deployment.

The Model Context Protocol (MCP) is a recently proposed interoperability standard that unifies how AI agents connect with external tools and data sources. By defining a set of common client-server message exchange clauses, MCP replaces fragmented integrations with a standardized, plug-and-play framework. However, to be compatible with diverse AI agents, the MCP specification relaxes many behavioral constraints into optional clauses, leading to misuse-prone SDK implementation. We identify it as a new attack surface that allows adversaries to achieve multiple attacks (e.g, silent prompt injection, DoS, etc.), named as \emph{compatibility-abusing attacks}. In this work, we present the first systematic framework for analyzing this new attack surface across multi-language MCP SDKs. First, we construct a universal and language-agnostic intermediate representation (IR) generator that normalizes SDKs of different languages. Next, based on the new IR, we propose auditable static analysis with LLM-guided semantic reasoning for cross-language/clause compliance analysis. Third, by formalizing the attack semantics of the MCP clauses, we build three attack modalities and develop a modality-guided pipeline to uncover exploitable non-compliance issues.

Most adversarial evaluations of large language model (LLM) safety assess single prompts and report binary pass/fail outcomes, which fails to capture how safety properties evolve under sustained adversarial interaction. We present ADVERSA, an automated red-teaming framework that measures guardrail degradation dynamics as continuous per-round compliance trajectories rather than discrete jailbreak events. ADVERSA uses a fine-tuned 70B attacker model (ADVERSA-Red, Llama-3.1-70B-Instruct with QLoRA) that eliminates the attacker-side safety refusals that render off-the-shelf models unreliable as attackers, scoring victim responses on a structured 5-point rubric that treats partial compliance as a distinct measurable state. We report a controlled experiment across three frontier victim models (Claude Opus 4.6, Gemini 3.1 Pro, GPT-5.2) using a triple-judge consensus architecture in which judge reliability is measured as a first-class research outcome rather than assumed. Across 15 conversations of up to 10 adversarial rounds, we observe a 26.7% jailbreak rate with an average jailbreak round of 1.25, suggesting that in this evaluation setting, successful jailbreaks were concentrated in early rounds rather than accumulating through sustained pressure. We document inter-judge agreement rates, self-judge scoring tendencies, attacker drift as a failure mode in fine-tuned attackers deployed out of their training distribution, and attacker refusals as a previously-underreported confound in victim resistance measurement. All limitations are stated explicitly. Attack prompts are withheld per responsible disclosure policy; all other experimental artifacts are released.

Cybersecurity threats are becoming increasingly sophisticated, making traditional defense mechanisms and manual red teaming approaches insufficient for modern organizations. While red teaming has long been recognized as an effective method to identify vulnerabilities by simulating real-world attacks, its manual execution is resource-intensive, time-consuming, and lacks scalability for frequent assessments. These limitations have driven the evolution toward auto-mated red teaming, which leverages artificial intelligence and automation to deliver efficient and adaptive security evaluations. This systematic review consolidates existing research on automated red teaming, examining its methodologies, tools, benefits, and limitations. The paper also highlights current trends, challenges, and research gaps, offering insights into future directions for improving automated red teaming as a critical component of proactive cybersecurity strategies. By synthesizing findings from diverse studies, this review aims to provide a comprehensive understanding of how automation enhances red teaming and strengthens organizational resilience against evolving cyber threats.