arXiv subjects

Wenbo Guo

Publications and source records attributed to Wenbo Guo.

At least 19 recordsLinked to original sources

arXiv2026

From Documentation to Zero-day Vulnerabilities: LLM-Driven Fuzzing of JavaScript Engines in PDF Readers

Existing fuzzers for PDF readers rely on simple test cases that involve only individual API calls, leading to limited coverage and potentially missing vulnerabilities that require sequences of API calls. To address these limitations, we propose PDFuzzer, a novel PDF engine fuzzer that automatically generates complex and meaningful API call sequences. PDFuzzer first uses a Large Language Model (LLM) to construct context-free grammars and infer the relationships between individual API calls from specifications extracted from JavaScript API manuals and execution traces. Based on the grammars and relationships, PDFuzzer employs a constraint solver to generate concrete API call sequences for fuzzing. Our experiments show that PDFuzzer significantly outperforms state-of-the-art PDF fuzzers (TypeOracle, Favocado, and Cooper) and LLM-based fuzzers (Fuzz4All, naive LLM) on three mainstream PDF readers: Adobe Acrobat Reader, Foxit PDF Reader, and PDF-XChange Editor. PDFuzzer achieves up to 48% higher coverage than existing tools and identifies 31 zero-day vulnerabilities in these readers, from information leakage to arbitrary code execution. Our ablation study validates the necessity of each component, including LLMs, which achieve high accuracy across all pipeline stages (93-98%). We disclosed all vulnerabilities to the vendors via a coordinated vulnerability disclosure process and received bug bounties.

cs.CR↗

arXiv2026

Mutate to Bypass: Autonomous Endpoint Evasion via Knowledge-Driven Multi-Agent Orchestration

Public reports and open-source resources expose many EDR evasion techniques, but it remains unclear whether commercial Endpoint Detection and Response (EDR) systems can withstand these documented attacks. Evaluating them requires turning fragmented security knowledge into working payloads and refining those payloads from opaque alerts, tasks that existing automation does not address. We present AutoBypass, a knowledge-grounded, closed-loop multi-agent framework for automated EDR resilience assessment. A Detection-Aware Knowledge Base structures threat intelligence, expert analyses, and open-source proofs of concept into evasion techniques and operational constraints. Agents use this knowledge to plan attacks, generate polymorphic code, and compile binaries, while a telemetry-driven reasoning engine diagnoses failures and feeds corrective evidence back into the strategy. Across seven commercial endpoint security platforms, AutoBypass bypassed every target, reaching 90% evasion against Windows Defender and 86.7% against Trend Micro AV. Ablations show that the knowledge base raises the success rates of 8B open-weight models from 27--53% to 43--83%, bringing them close to large proprietary models. These results demonstrate a systematic way to operationalize public security knowledge for continuous, automated assessment of EDR resilience.

cs.CR↗

arXiv2026

Skills That Don't Exist: A Large-Scale Study of Hallucinated Skill Recommendation in LLM Agents

LLM agents acquire new capabilities by downloading skills from open registries. Instead of browsing these catalogs manually, developers typically ask the agent to recommend and install a skill. This convenience hides a risk: agents frequently invent names for skills that exist in no registry. We term this flaw skill name hallucination. A fake name may seem harmless, but it opens the door to supply-chain attacks. Because registries rarely verify publishers, an adversary can prompt the agent, collect the fake names it returns, pre-register malicious skills under them, and wait for a victim to install the payload. We conducted the first large-scale measurement of skill name hallucination, evaluating 15,000 prompts across 12 configurations (4 standalone LLMs and 8 agents). We conservatively counted a name as hallucinated only if it was missing from all live registries and GitHub. The results reveal a systemic vulnerability: every configuration hallucinates. Rates average 36.0% for standalone LLMs and 36.9% for agents, rising to 43.1% on real-world developer questions. In total, the systems generated 5,669 distinct hallucinated names. Crucially, these names are not random noise. Agents repeat the same fake names across prompts and models, giving attackers highly reliable targets to hijack. Finally, we tested four model-level defenses and found a severe conflict between security and usability. The strongest, retrieval grounding, cut the hallucination rate from 40.8% to 3.2% but crippled usefulness: even the best-defended system recommended the correct skill only about one in six times. Skill name hallucination is thus a highly exploitable vulnerability requiring minimal attacker effort. Fixing it cannot rely on prompt engineering or model tuning alone. It demands ecosystem-wide structural changes: registry-level name reservations and verified recommendation pipelines.

cs.SE↗

arXiv2026

SeedSmith: LLM-Driven Seed Synthesis for Directed Fuzzing

Directed fuzzing steers fuzzers toward user-defined sink functions to identify vulnerabilities, but it frequently fails to trigger crashes even after long campaigns. We identify two challenges that prevent directed fuzzers from exposing crashes: incomplete static analysis of indirect calls, which leaves reachable paths invisible to distance-based guidance, and lack of semantic guidance for crash preconditions, which blind mutation cannot satisfy within practical time budgets. A natural intervention point is the initial seed corpus: seeds that encode the right control-flow path and satisfy key crash preconditions shift fuzzing from blind exploration to local refinement. Existing seed generation approaches address neither: grammar-based and format-driven methods produce structurally valid inputs with no sink awareness, while LLM-based methods either lack sink targeting or inherit static analysis limitations through one-shot prompting. We present SeedSmith, an agentic LLM pipeline that replicates a security analyst's workflow: starting from a sink, it iteratively explores the codebase, resolves indirect calls, identifies crash preconditions, and synthesizes concrete inputs that satisfy them. Because SeedSmith operates as a seed generation front-end, its seeds are fuzzer-agnostic and improve any downstream mutation-based fuzzer without modification. On Magma, fuzzers using SeedSmith seeds achieve geometric mean crash-time speedups of 11.51 times (AFL++) to 14.66 times (AFLGo) over default seeds. On ARVO, SeedSmith enables fuzzers to trigger 16 previously unreachable bugs spanning 10 projects with diverse input formats.

cs.CR↗

arXiv2026

When Do Intrinsic Rewards Work for Code Reasoning? A Comprehensive Study

Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in large language model reasoning, but relies on ground-truth supervision that is costly or infeasible, especially in coding tasks. Recent work addresses this by deriving rewards from a model's own signals, such as majority voting or confidence-based scores, achieving notable success on mathematical reasoning benchmarks. However, code generation poses distinct challenges: programs are structurally complex, semantically equivalent solutions may differ syntactically, and verification typically requires execution. Whether these intrinsic reward methods transfer effectively to code remains unexplored. In this work, we present a systematic empirical study of intrinsic reward methods for code generation. We conduct extensive experiments on LiveCodeBench, systematically evaluating representative certainty-based Reinforcement Learning from Internal Feedback (RLIF) approaches under different training scenarios and hyperparameter settings. Our experiments reveal that certainty-based methods yield early gains but inevitably collapse: models progressively shorten outputs and lose reasoning capability, with collapse speed sensitive to sample size and temperature. When used to initialize RLVR training, RLIF pre-training offers no significant improvement over training from scratch. We also provide actionable recommendations for using intrinsic rewards for training code reasoning models. Our study shows both the promise and limitations of intrinsic reward methods for code, informing future work on code models and agents.

cs.AI↗

arXiv2026

Seeing Is Not Screening: Multimodal Hidden Instruction Attacks on Agent Skill Scanners

Agent skills are emerging as an important attack surface in LLM-based systems. Through an empirical study of existing skill scanners, we find that current defenses primarily rely on textual descriptions, manifests, and source code as the main signals for security analysis, which can leave visually conveyed malicious intent insufficiently examined. This creates a practical blind spot: harmful operational instructions hidden in images may bypass scanning while still being recoverable by multimodal agents during deployment. To systematically investigate this threat, we propose SkillCamo, a document-mediated multimodal instruction attack that conceals malicious instructions within images bundled with a skill while rewriting the surrounding documentation to naturally reference those images as part of the normal workflow. Thus, the attack does not rely on the image alone, but on the joint interpretation of textual guidance and visual payload at execution time. To defend against such attacks, we further propose ExecScan, an execution-grounded multimodal scanning module that performs intent extraction, behavior reconstruction, abuse assessment, and deliberative execution simulation over skill artifacts. ExecScan jointly analyzes documentation, code, referenced resources, and visual content to recover hidden instructions, reconstruct executable behavior chains, and identify downstream risks such as exfiltration, destruction, persistence, deception, and privilege escalation. Extensive experiments show that image-hidden malicious instructions challenge existing skill scanners, while ExecScan can improve the skill scanning performance.

cs.CR↗

arXiv2026

MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systems

Hierarchical multi-agent systems (MAS) are rapidly being deployed in high-stakes workflows across domains such as finance and software engineering. In these systems, safety and security are inherently distributed across role-specialized agents, significantly expanding the attack surface, particularly under coordinated adversarial behaviors such as privilege escalation and cross-agent collusion. Existing red-teaming approaches for MAS remain limited: they rely on heuristic selection of target agents and perturb isolated message streams, leaving critical questions unanswered as which agents are most responsible for system safety, and how compromised agents can coordinate to bypass defenses. We propose MAStrike, a closed-loop framework for collusive red-teaming in hierarchical MAS. We propose the first agent-level Shapley value analysis for MAS, quantifying each agent's marginal contribution to system robustness under task-specific distributions. GGuided by this attribution, MAStrike identifies vulnerable agent coalitions and generates coordinated, role-aware adversarial manipulations. These attacks are iteratively refined through structured causal diagnosis, attributing failure cases to uncompromised agents that block adversarial attempts. We further build a comprehensive MAS red-teaming benchmark and controllable environments spanning diverse hierarchical topologies and domains, including finance, software engineering, and CRM. Extensive experiments across MAS built on multiple frontier models show that MAStrike substantially outperforms heuristic baselines. Our analysis further uncovers non-trivial Shapley value distributions and higher-order interaction structures among agents, revealing critical vulnerabilities and coordination patterns that are overlooked by prior single-agent or template-based methods.

cs.CR↗

arXiv2026

AgentBeats: Agentifying Agent Assessment for Openness, Standardization, and Reproducibility

Agent systems are advancing quickly across domains, but their evaluation remains fragmented. Most benchmarks rely on fixed, LLM-centric harnesses that require heavy integration, create test-production mismatch, and limit fair comparison across diverse agent designs. The root problem is the lack of an open, agent-agnostic assessment interface. We advocate Agentified Agent Assessment (AAA), where evaluation is performed by judge agents and all participants interact through standardized protocols: A2A for task management and MCP for tool access. Conventional benchmarking defines two separate interfaces, one for the benchmark and one for the agent, while AAA only needs one; this yields a generic, unified framework that separates assessment logic from agent implementation and enables reproducible, interoperable, and multi-agent evaluation. We further introduce AgentBeats as a concrete realization of AAA: we identify five practical operation modes that make standardized assessment compatible with real-world constraints on openness, privacy, and reproducibility. To evaluate our design at scale, we conduct two studies: a five-month open competition that drew 298 judge agents across 12 categories together with 467 subject agents from independent participants, showing that AAA applies across a heterogeneous range of benchmarks; and a case study on coding agents that confirms agentified evaluation preserves fidelity with the public record while surfacing previously missing head-to-head results, yielding research insights about agent design. Combining a community-scale field study and a controlled coding case study, we verify that AAA delivers coverage, practicality, and fidelity across heterogeneous scenarios at scale. Together, AAA and AgentBeats offer a clear path toward open, standardized, and reproducible agent assessment.

cs.AI↗

arXiv2026

MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills

AI coding agents such as Claude Code and Gemini CLI increasingly extend themselves with third-party skills: markdown packages bundling natural-language instructions, executable scripts, and tool permissions. Because a skill is at once code and agent-facing instruction, it introduces a supply chain dependency whose risk is neither pure code nor pure prompt. Detection tools have never been measured against verified ground truth spanning this hybrid space, leaving their effectiveness unknown and wild-only evaluations biased. We present MalSkillBench, the first runtime-verified benchmark of malicious agent skills: 3,944 malicious skills labeled along a three-dimensional taxonomy of 108 cells. Of these, 3,214 come from a closed-loop Generate-Verify-Feedback pipeline admitting only samples whose malicious behavior fires inside a Docker sandbox under system-call monitoring and an LLM judge; we add 703 in-the-wild and 4,000 matched benign skills. Our measurements are consistent: code injection reaches 94.5% verification yield but prompt injection only 75.8%, the same fragility that later makes it hard to detect; the wild sample is narrow, dominated by one cryptocurrency-theft campaign (86.6% one behavior, 81% from two accounts) with a small but architecturally new tail attacking the agent control plane; the strongest skill-specific detector reaches 98.4% recall on code injection yet collapses on prompt-injection and agent-control attacks, and wild-only scoring swings the ranking by up to 66 recall points; supply-chain scanners and prompt-injection defenses each see only half of a skill, and no combination recovers the code-instruction relationship. Detecting malicious skills therefore requires reasoning jointly over task intent, code, and instructions. We release the dataset, pipeline, baselines, and results.

cs.CR↗

arXiv2026

CyberGym-E2E: Scalable Real-World Benchmark for AI Agents' End-to-End Cybersecurity Capabilities

AI has the potential to transform cybersecurity by enabling systems that can autonomously detect, analyze, and remediate software vulnerabilities. However, existing cybersecurity evaluations of AI systems are limited in scale or scope, and fail to capture the end-to-end lifecycle of real-world software vulnerability discovery and remediation. To address this gap, we propose CyberGym-E2E, a large-scale and realistic end-to-end cybersecurity benchmark that comprehensively evaluates AI agents' abilities across the full lifecycle of vulnerability discovery, PoC generation, and patch generation. CyberGym-E2E is comprehensive and scalable, as we build an automated, agent-enhanced pipeline for transforming open-source vulnerability data into realistic evaluation environments. Currently, the benchmark consists of 920 real-world vulnerabilities across 139 different open-source projects.

cs.CR↗

arXiv2026

MalwarePT: A Binary-Level Foundation Model for Malware Analysis

Automated malware analysis increasingly relies on machine learning, yet most existing methods remain task-specific and depend on handcrafted features or narrowly scoped models. Recent developments in binary-level foundation models suggest a path toward reusable program representations, but their application to malware analysis remains underexplored, and most still operate at byte-level tokenization, limiting their ability to capture multi-byte code patterns. In this work, we introduce MalwarePT, a binary-level foundation model for malware analysis built on a ModernBERT-style encoder and pretrained with masked language modeling on Windows PE code-section bytes. We study whether a single pretrained encoder can transfer across malware-analysis tasks at different granularities, and how tokenization design affects that transfer. We train a byte-pair encoding (BPE) tokenizer on code-section bytes to compress frequent multi-byte patterns within a fixed context budget. We evaluate MalwarePT on three downstream tasks spanning token-, function-, and document-level prediction: API call prediction, functionality classification, and malware (program) detection under temporal drift. Our evaluation demonstrates that pretraining yields substantial gains for API call prediction and functionality classification, and that increasing the BPE vocabulary beyond the byte-level baseline improves performance, with the strongest overall tradeoff at a vocabulary size of 1,024 tokens. In malware detection at FPR ~ 0.001, MalwarePT outperforms the neural network baselines, and is complementary to feature-engineering models that rely on PE structure. We also compare against existing binary foundation models and show that MalwarePT's design choices yield gains across all downstream tasks.

cs.CR↗

arXiv2026

Progent: Securing AI Agents with Privilege Control

AI agents interact with external environments through tool calls, exposing them to attacks like indirect prompt injection that can trigger unauthorized actions. Securing these agents is challenging: they behave autonomously and probabilistically, security requirements evolve depending on the user's task and execution state, and there is an inherent tradeofff between security and utility. In this work, we introduce Progent, a novel framework that secures AI agents via privilege control. Progent represents privilege as a security policy consisting of symbolic rules over tool names and arguments. These rules specify which tool calls are allowed for task completion and which unnecessary ones are blocked for security. Every tool call is checked against such a policy through a deterministic procedure, enforcing the principle of least privilege. To handle diverse user tasks and evolving execution contexts, an LLM automatically generates the initial policy from the user's task and updates it during execution as new information arrives. Each proposed update is determined by an SMT solver to be either a narrowing (applied automatically) or an expansion (requiring explicit approval), ensuring that the agent's effective action space can only shrink without approval (monotonic confinement). This deterministic update mechanism preserves utility and prevents silent privilege escalation, even when adversarial inputs are present. Our evaluation on popular benchmarks (i.e., AgentDojo and ASB) shows that Progent significantly reduces attack success rates while maintaining high utility. We further validate Progent's practicality by showcasing its effectiveness in real-world agent frameworks such as LangChain and OpenAI Agents SDK.

cs.CR↗

arXiv2026

netFound: Principled Design for Network Foundation Models

Network foundation models promise reusable representations for diverse traffic analysis tasks, but recent diagnostic works have revealed fundamental problems: models exploit dataset shortcuts rather than learning genuine traffic patterns, produce collapsed embedding spaces, and fail to capture the exogenous network conditions that shape real-world behavior. We translate these diagnostic insights into four concrete design principles: protocol-aware tokenization, operational context embedding, burst-flow hierarchical attention, and privacy-by-construction input design, and build netFound, a network foundation model whose architecture is motivated by this failure analysis. We pretrain netFound on a billion-token-scale corpus over 5000 GPU hours, and demonstrate that it produces high-quality representations with lower anisotropy, significantly higher alignment with domain-expert features, and an F1 of 0.95 on exogenous context discrimination where existing state-of-the-art models score below 0.62, while preserving privacy by excluding payload and IP addresses. netFound demonstrates significant improvements in frozen-encoder evaluation, showing that pretrained embeddings themselves carry useful structure, and remains the top performer across all benchmarks in end-to-end fine-tuned settings. We release full open-source code, weights for three model sizes on HuggingFace, a containerized pipeline from raw PCAPs to downstream inference, and the full 4.2 billion flows pretraining dataset to facilitate reproducibility and further research.

cs.NI↗

arXiv2026

ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?

AI agents are rapidly gaining capabilities that could significantly reshape cybersecurity, making rigorous evaluation urgent. A critical capability is exploitation: turning a vulnerability, which is not yet an attack, into a concrete security impact, such as unauthorized file access or code execution. Exploitation is a particularly challenging task because it requires low-level program reasoning (e.g., about memory layout), runtime adaptation, and sustained progress over long horizons. Meanwhile, it is inherently dual-use, supporting defensive workflows while lowering the barrier for offense. Despite its importance and diagnostic value, exploitation remains under-evaluated. To address this gap, we introduce ExploitGym, a large-scale, diverse, realistic benchmark on the exploitation capabilities of AI agents. Given a program input that triggers a vulnerability, ExploitGym tasks agents with progressively extending it into a working exploit. The benchmark comprises 898 instances sourced from real-world vulnerabilities across three domains, including userspace programs, Google's V8 JavaScript engine, and the Linux kernel. We vary the security protections applied to each instance, isolating their impact on agent performance. All configurations are packaged in reproducible containerized environments. Our evaluation shows that while exploitation remains challenging, frontier models can successfully exploit a non-trivial fraction of vulnerabilities. For example, the strongest configurations are Anthropic's latest model Claude Mythos Preview and OpenAI's GPT-5.5, which produce working exploits for 157 and 120 instances, respectively. Notably, even with widely used defenses enabled, models retain non-trivial success rates. These results establish ExploitGym as an effective testbed for exploitation and highlight the growing cybersecurity risks posed by increasingly capable AI agents.

cs.CR↗

arXiv2026

DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents

AI agents are increasingly deployed across diverse domains to automate complex workflows through long-horizon and high-stakes action executions. Due to their high capability and flexibility, such agents raise significant security and safety concerns. A growing number of real-world incidents have shown that adversaries can easily manipulate agents into performing harmful actions, such as leaking API keys, deleting user data, or initiating unauthorized transactions. Evaluating agent security is inherently challenging, as agents operate in dynamic, untrusted environments involving external tools, heterogeneous data sources, and frequent user interactions. However, realistic, controllable, and reproducible environments for large-scale risk assessment remain largely underexplored. To address this gap, we introduce the DecodingTrust-Agent Platform (DTap), the first controllable and interactive red-teaming platform for AI agents, spanning 14 real-world domains and over 50 simulation environments that replicate widely used systems such as Google Workspace, Paypal, and Slack. To scale the risk assessment of agents in DTap, we further propose DTap-Red, the first autonomous red-teaming agent that systematically explores diverse injection vectors (e.g., prompt, tool, skill, environment, combinations) and autonomously discovers effective attack strategies tailored to varying malicious goals. Using DTap-Red, we curate DTap-Bench, a large-scale red-teaming dataset comprising high-quality instances across domains, each paired with a verifiable judge to automatically validate attack outcomes. Through DTap, we conduct large-scale evaluations of popular AI agents built on various backbone models, spanning security policies, risk categories, and attack strategies, revealing systematic vulnerability patterns and providing valuable insights for developing secure next-generation agents.

cs.AI↗

arXiv2026

Program Analysis Guided LLM Agent for Proof-of-Concept Generation

Software developers frequently receive vulnerability reports that require them to reproduce the vulnerability in a reliable manner by generating a proof-of-concept (PoC) input that triggers it. Given the source code for a software project and a specific code location for a potential vulnerability, automatically generating a PoC for the given vulnerability has been a challenging research problem. Symbolic execution and fuzzing techniques require expert guidance and manual steps and face scalability challenges for PoC generation. Although recent advances in LLMs have increased the level of automation and scalability, the success rate of PoC generation with LLMs remains quite low. In this paper, we present a novel approach called Program Analysis Guided proof of concept generation agENT (PAGENT) that is scalable and significantly improves the success rate of automated PoC generation compared to prior results. PAGENT integrates lightweight and rule-based static analysis phases for providing static analysis guidance and sanitizer-based profiling and coverage information for providing dynamic analysis guidance with a PoC generation agent. Our experiments demonstrate that the resulting hybrid approach significantly outperforms the prior top-performing agentic approach by 132% for the PoC generation task.

cs.SE↗

arXiv2026

Guiding Symbolic Execution with Static Analysis and LLMs for Vulnerability Discovery

Symbolic execution detects vulnerabilities with precision, but applying it to large codebases requires harnesses that set up symbolic state, model dependencies, and specify assertions. Writing these harnesses has traditionally been a manual process requiring expert knowledge, which significantly limits the scalability of the technique. We present Static Analysis Informed and LLM-Orchestrated Symbolic Execution (SAILOR), which automates symbolic execution harness construction by combining static analysis with LLM-based synthesis. SAILOR operates in three phases: (1) static analysis identifies candidate vulnerable locations and generates vulnerability specifications; (2) an LLM uses vulnerability specifications and orchestrates harness synthesis by iteratively refining drivers, stubs, and assertions against compiler and symbolic execution feedback; symbolic execution then detects vulnerabilities using the generated harness, and (3) concrete replay validates the symbolic execution results against the unmodified project source. This design combines the scalability of static analysis, the code reasoning of LLMs, the path precision of symbolic execution, and the ground truth produced by concrete execution. We evaluate SAILOR on 10 open-source C/C++ projects totaling 6.8 M lines of code. SAILOR discovers 379 distinct, previously unknown memory-safety vulnerabilities (421 confirmed crashes). The strongest of five baselines we compare SAILOR to (agentic vulnerability detection using Claude Code with full codebase access and unlimited interaction), finds only 12 vulnerabilities. Each phase of SAILOR is critical: Without static analysis targeting confirmed vulnerabilities drop 12.2X; without iterative LLM synthesis zero vulnerabilities are confirmed; and without symbolic execution no approach can detect more than 12 vulnerabilities.

cs.CR↗

arXiv2026

ShieldNet: Network-Level Guardrails against Emerging Supply-Chain Injections in Agentic Systems

Existing research on LLM agent security mainly focuses on prompt injection and unsafe input/output behaviors. However, as agents increasingly rely on third-party tools and MCP servers, a new class of supply-chain threats has emerged, where malicious behaviors are embedded in seemingly benign tools, silently hijacking agent execution, leaking sensitive data, or triggering unauthorized actions. Despite their growing impact, there is currently no comprehensive benchmark for evaluating such threats. To bridge this gap, we introduce SC-Inject-Bench, a large-scale benchmark comprising over 10,000 malicious MCP tools grounded in a taxonomy of 25+ attack types derived from MITRE ATT&CK targeting supply-chain threats. We observe that existing MCP scanners and semantic guardrails perform poorly on this benchmark. Motivated by this finding, we propose ShieldNet, a network-level guardrail framework that detects supply-chain poisoning by observing real network interactions rather than surface-level tool traces. ShieldNet integrates a man-in-the-middle (MITM) proxy and an event extractor to identify critical network behaviors, which are then processed by a lightweight classifier for attack detection. Extensive experiments show that ShieldNet achieves strong detection performance (up to 0.995 F-1 with only 0.8% false positives) while introducing little runtime overhead, substantially outperforming existing MCP scanners and LLM-based guardrails.

cs.AI↗