Autonomous agent frameworks built upon large language models (LLMs) are evolving into complex, tool-integrated, and continuously operating systems, introducing security risks beyond traditional prompt-level vulnerabilities. As this paradigm is still at an early stage of development, a timely and systematic understanding of its security implications is increasingly important. Although a growing body of work has examined different attack surfaces and defense problems in agent systems, existing studies remain scattered across individual aspects of agent security, and there is still a lack of a layered review on this topic. To address this gap, this survey presents a layered review of security risks and defense strategies in autonomous agent frameworks, with OpenClaw as a case study. We organize the analysis into four security-relevant layers: the context and instruction layer, the tool and action layer, the state and persistence layer, and the ecosystem and automation layer. For each layer, we summarize its functional role, representative security risks, and corresponding defense strategies. Based on this layered analysis, we further identify that threats in autonomous agent frameworks may propagate across layers, from manipulated inputs to unsafe actions, persistent state contamination, and broader ecosystem-level impact. Finally, we highlight potential key challenges, including research imbalance across layers, the lack of long-horizon evaluation, and weak ecosystem trust models, and outline future directions toward more systematic and integrated defenses.

Structured-workflow agents driven by large language models execute tool calls against sensitive external environments. We propose \codename, a telemetry-driven behavioral anomaly detection firewall. Drawing on sequence-based intrusion detection, \codename\ compiles verified benign tool-call telemetry into a parameterized deterministic finite automaton (pDFA). The model defines permitted tool sequences, sequential contexts, and parameter bounds. At runtime, a lightweight gateway enforces these boundaries via an $O(1)$ state-transition structural lookup, shifting computationally expensive analysis entirely offline. Evaluated on the Agent Security Bench (ASB), \codename\ achieves a 5.6\% macro-averaged attack success rate (ASR) across five scenarios. Within three structured workflows, ASR drops to 2.2\%, outperforming Aegis, a state-of-the-art stateless scanner, at 12.8\%. \codename\ achieves 0\% ASR on multi-step and context-sequential attacks in structured settings. Furthermore, against 1,000 algorithmically spliced exfiltration payloads, only 1.4\% matched valid structural paths, all of which failed end-to-end string parameter guards (0 successes out of 14 surviving paths, 95\% CI [0\%, 23.2\%]). \codename\ introduces just 2.2~ms of per-call latency (a 3.7$\times$ speedup over \textsc{Aegis}) while maintaining a 2.0\% benign task failure rate (BTFR) on benign workloads. Modeling the behavioral trajectory effectively collapses the available attack surface, but unmaintained continuous parameter bounds remain vulnerable to synonym-substitution attacks (18\% evasion rate). Thus, exact-match whitelisting of sensitive parameters ultimately bears the final defensive load against execution.

This report presents a comparative evaluation of DKnownAI Guard in AI agent security scenarios, benchmarked against three competing products: AWS Bedrock Guardrails, Azure Content Safety, and Lakera Guard. Using human annotation as the ground truth, we assess each guardrail's ability to detect two categories of risks: threats to the agent itself (e.g., instruction override, indirect injection, tool abuse) and requests intended to elicit harmful content (e.g., hate speech, pornography, violence). Evaluation results demonstrate that DKnownAI Guard achieves the highest recall rate at 96.5\% and ranks first in true negative rate (TNR) at 90.4\%, delivering the best overall performance among all evaluated guardrails.

Agentic AI systems face security challenges that stateless large language models do not. They plan across extended horizons, maintain persistent memory, invoke external tools, and coordinate with peer agents. Existing security analyses organize threats by attack type (prompt injection, jailbreaking), but provide no principled model of which architectural component is vulnerable or over what timescale the threat manifests. This paper makes five contributions. First, we introduce the Layered Attack Surface Model (LASM), a seven-layer framework that maps threats to distinct architectural components: Foundation, Cognitive, Memory, Tool Execution, Multi-Agent Coordination, Ecosystem, and Governance, the accountability and observability layer that spans the stack analogously to the network management plane. Second, we introduce attack temporality as an orthogonal analytical dimension with four classes: Instantaneous (T1), Session-Persistent (T2), Cross-Session Cumulative (T3), and Sub-Session-Stack, Non-Session-Bounded (T4). Third, through a systematic review of 94 papers (2021--2025), we show that the most dangerous emerging threats concentrate at the intersection of high-layer attacks (L5--L7) and slow-burn temporality (T3--T4): covert agent collusion, long-term memory poisoning, MCP supply-chain compromise, and alignment failure that manifests as an insider threat with no external adversary. Only 8 of 120 paper-cell assignments (7%) fall in this zone. Fourth, we propose a cross-layer defense taxonomy spanning all seven LASM layers and all four temporality classes, exposing which threat classes existing defenses leave unaddressed. Fifth, we survey evaluation benchmarks, identify five research gaps in the under-studied high-layer, slow-burn zone, and argue that agentic security must be treated as a distributed systems problem embedded in an adversarial ecosystem.

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.

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.

The growth of agentic AI has drawn significant attention to function calling Large Language Models (LLMs), which are designed to extend the capabilities of AI-powered system by invoking external functions. Injection and jailbreaking attacks have been extensively explored to showcase the vulnerabilities of LLMs to user prompt manipulation. The expanded capabilities of agentic models introduce further vulnerabilities via their function calling interface. Recent work in LLM security showed that function calling can be abused, leading to data tampering and theft, causing disruptive behavior such as endless loops, or causing LLMs to produce harmful content in the style of jailbreaking attacks. This paper introduces a novel function hijacking attack (FHA) that manipulates the tool selection process of agentic models to force the invocation of a specific, attacker-chosen function. While existing attacks focus on semantic preference of the model for function-calling tasks, we show that FHA is largely agnostic to the context semantics and robust to the function sets, making it applicable across diverse domains. We further demonstrate that FHA can be trained to produce universal adversarial functions, enabling a single attacked function to hijack tool selection across multiple queries and payload configurations. We conducted experiments on 5 different models, including instructed and reasoning variants, reaching 70% to 100% ASR over the established BFCL dataset. Our findings further demonstrate the need for strong guardrails and security modules for agentic systems.

The transition of agentic AI from brittle prototypes to production systems is stalled by a pervasive crisis of craft. We suggest that the prevailing orchestration paradigm-delegating the system control loop to large language models and merely patching with heuristic guardrails-is the root cause of this fragility. Instead, we propose Arbiter-K, a Governance-First execution architecture that reconceptualizes the underlying model as a Probabilistic Processing Unit encapsulated by a deterministic, neuro-symbolic kernel. Arbiter-K implements a Semantic Instruction Set Architecture (ISA) to reify probabilistic messages into discrete instructions. This allows the kernel to maintain a Security Context Registry and construct an Instruction Dependency Graph at runtime, enabling active taint propagation based on the data-flow pedigree of each reasoning node. By leveraging this mechanism, Arbiter-K precisely interdicts unsafe trajectories at deterministic sinks (e.g., high-risk tool calls or unauthorized network egress) and enables autonomous execution correction and architectural rollback when security policies are triggered. Evaluations on OpenClaw and NanoBot demonstrate that Arbiter-K enforces security as a microarchitectural property, achieving 76% to 95% unsafe interception for a 92.79% absolute gain over native policies. The code is publicly available at https://github.com/cure-lab/ArbiterOS.

Large Language Model (LLM) agents provide powerful automation capabilities, but they also create a substantially broader attack surface than traditional applications due to their tight integration with non-deterministic models and third-party services. While current deployments primarily rely on cloud-hosted services, emerging designs increasingly execute agents directly on edge devices to reduce latency and enhance user privacy. However, securely hosting such complex agent pipelines on edge devices remains challenging. These deployments must protect proprietary assets (e.g., system prompts and model weights) and sensitive runtime state on heterogeneous platforms that are vulnerable to software attacks and potentially controlled by malicious users. To address these challenges, we present AgenTEE, a system for deploying confidential agent pipelines on edge devices. AgenTEE places the agent runtime, inference engine, and third-party applications into independently attested confidential virtual machines (cVMs) and mediates their interaction through explicit, verifiable communication channels. Built on Arm Confidential Compute Architecture (CCA), a recent extension to Arm platforms, AgenTEE enforces strong system-level isolation of sensitive assets and runtime state. Our evaluation shows that such multi-cVMs system is practical, achieving near-native performance with less than 5.15% runtime overhead compared to commodity OS multi-process deployments.

Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection. This paper presents SafeAgent, a runtime security architecture that treats agent safety as a stateful decision problem over evolving interaction trajectories. The proposed design separates execution governance from semantic risk reasoning through two coordinated components: a runtime controller that mediates actions around the agent loop and a context-aware decision core that operates over persistent session state. The core is formalized as a context-aware advanced machine intelligence and instantiated through operators for risk encoding, utility-cost evaluation, consequence modeling, policy arbitration, and state synchronization. Experiments on Agent Security Bench (ASB) and InjecAgent show that SafeAgent consistently improves robustness over baseline and text-level guardrail methods while maintaining competitive benign-task performance. Ablation studies further show that recovery confidence and policy weighting determine distinct safety-utility operating points.

Model Context Protocol (MCP) is a rapidly adopted standard for defining and invoking external tools in LLM applications. The multi-layered architecture of MCP introduces new attack surfaces such as tool poisoning, in addition to traditional prompt injection. Existing defense systems suffer from limitations including high false positive rates, API dependency, or white-box access requirements. In this study, we propose CASCADE, a three-tiered cascaded defense architecture for MCP-based systems: (i) Layer 1 performs fast pre-filtering using regex, phrase weighting, and entropy analysis; (ii) Layer 2 conducts semantic analysis via BGE embedding with an Ollama Llama3 fallback mechanism; (iii) Layer 3 applies pattern-based output filtering. Evaluation on a dataset of 5,000 samples yielded 95.85% precision, 6.06% false positive rate, 61.05% recall, and 74.59% F1-score. Analysis across 31 attack types categorized into 6 tiers revealed high detection rates for data exfiltration (91.5%) and prompt injection (84.2%), while semantic attack (52.5%) and tool poisoning (59.9%) categories showed potential for improvement. A key advantage of CASCADE over existing solutions is its fully local operation, requiring no external API calls

Modern AI agents routinely depend on secrets such as API keys and SSH credentials, yet the dominant deployment model still exposes those secrets directly to the agent process through environment variables, local files, or forwarding sockets. This design fails against prompt injection, tool misuse, and model-controlled exfiltration because the agent can both use and reveal the same bearer credential. We present CapSeal, a capability-sealed secret mediation architecture that replaces direct secret access with constrained invocations through a local trusted broker. CapSeal combines capability issuance, schema-constrained HTTP execution, broker-executed SSH actions, anti-replay session binding, policy evaluation, and tamper-evident audit trails. We describe a Rust prototype integrated with an MCP-facing adapter, formulate conditional security goals for non-disclosure, constrained use, replay resistance, and auditability, and define an evaluation plan spanning prompt injection, tool misuse, and SSH abuse. The resulting system reframes secret handling for agentic systems from handing the model a key to granting the model a narrowly scoped, non-exportable action capability.

Most LLM safety work studies single-agent models, but many real applications rely on multiple interacting agents. In these systems, prompt segmentation and inter-agent routing create attack surfaces that single-agent evaluations miss. We study \emph{conjunctive prompt attacks}, where a trigger key in the user query and a hidden adversarial template in one compromised remote agent each appear benign alone but activate harmful behavior when routing brings them together. We consider an attacker who changes neither model weights nor the client agent and instead controls only trigger placement and template insertion. Across star, chain, and DAG topologies, routing-aware optimization substantially increases attack success over non-optimized baselines while keeping false activations low. Existing defenses, including PromptGuard, Llama-Guard variants, and system-level controls such as tool restrictions, do not reliably stop the attack because no single component appears malicious in isolation. These results expose a structural vulnerability in agentic LLM pipelines and motivate defenses that reason over routing and cross-agent composition. Code is available at https://github.com/UCF-ML-Research/ConjunctiveAgents.

The performance of large language model (LLM) agents depends critically on the execution harness, the system layer that orchestrates tool use, context management, and state persistence. Yet this same architectural centrality makes the harness a high-value attack surface: a single compromise at the harness level can cascade through the entire execution pipeline. We observe that existing security approaches suffer from structural mismatch, leaving them blind to harness-internal state and unable to coordinate across the different phases of agent operation. In this paper, we introduce \safeharness{}, a security architecture in which four proposed defense layers are woven directly into the agent lifecycle to address above significant limitations: adversarial context filtering at input processing, tiered causal verification at decision making, privilege-separated tool control at action execution, and safe rollback with adaptive degradation at state update. The proposed cross-layer mechanisms tie these layers together, escalating verification rigor, triggering rollbacks, and tightening tool privileges whenever sustained anomalies are detected. We evaluate \safeharness{} on benchmark datasets across diverse harness configurations, comparing against four security baselines under five attack scenarios spanning six threat categories. Compared to the unprotected baseline, \safeharness{} achieves an average reduction of approximately 38\% in UBR and 42\% in ASR, substantially lowering both the unsafe behavior rate and the attack success rate while preserving core task utility.

Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect prompt injection. Adversaries exploit this weakness by embedding malicious instructions within tool-returned content, which agents directly incorporate into their conversation history as trusted observations. This vulnerability manifests across three primary attack channels: web and local content injection, MCP server injection, and skill file injection. To address these vulnerabilities, we introduce \textsc{ClawGuard}, a novel runtime security framework that enforces a user-confirmed rule set at every tool-call boundary, transforming unreliable alignment-dependent defense into a deterministic, auditable mechanism that intercepts adversarial tool calls before any real-world effect is produced. By automatically deriving task-specific access constraints from the user's stated objective prior to any external tool invocation, \textsc{ClawGuard} blocks all three injection pathways without model modification or infrastructure change. Experiments across five state-of-the-art language models on AgentDojo, SkillInject, and MCPSafeBench demonstrate that \textsc{ClawGuard} achieves robust protection against indirect prompt injection without compromising agent utility. This work establishes deterministic tool-call boundary enforcement as an effective defense mechanism for secure agentic AI systems, requiring neither safety-specific fine-tuning nor architectural modification. Code is publicly available at https://github.com/Claw-Guard/ClawGuard.

Autonomous language-model agents increasingly rely on installable skills and tools to complete user tasks. Static skill auditing can expose capability surface before deployment, but it cannot determine whether a particular invocation is unsafe under the current user request and runtime context. We therefore study skill invocation auditing as a continuous-risk estimation problem: given a user request, candidate skill, and runtime context, predict a score that supports ranking and triage before a hard intervention is applied. We introduce STARS, which combines a static capability prior, a request-conditioned invocation risk model, and a calibrated risk-fusion policy. To evaluate this setting, we construct SIA-Bench, a benchmark of 3,000 invocation records with group-safe splits, lineage metadata, runtime context, canonical action labels, and derived continuous-risk targets. On a held-out split of indirect prompt injection attacks, calibrated fusion reaches 0.439 high-risk AUPRC, improving over 0.405 for the contextual scorer and 0.380 for the strongest static baseline, while the contextual scorer remains better calibrated with 0.289 expected calibration error. On the locked in-distribution test split, gains are smaller and static priors remain useful. The resulting claim is therefore narrower: request-conditioned auditing is most valuable as an invocation-time risk-scoring and triage layer rather than as a replacement for static screening. Code is available at https://github.com/123zgj123/STARS.

Large language model (LLM) agents increasingly rely on third-party API routers to dispatch tool-calling requests across multiple upstream providers. These routers operate as application-layer proxies with full plaintext access to every in-flight JSON payload, yet no provider enforces cryptographic integrity between client and upstream model. We present the first systematic study of this attack surface. We formalize a threat model for malicious LLM API routers and define two core attack classes, payload injection (AC-1) and secret exfiltration (AC-2), together with two adaptive evasion variants: dependency-targeted injection (AC-1.a) and conditional delivery (AC-1.b). Across 28 paid routers purchased from Taobao, Xianyu, and Shopify-hosted storefronts and 400 free routers collected from public communities, we find 1 paid and 8 free routers actively injecting malicious code, 2 deploying adaptive evasion triggers, 17 touching researcher-owned AWS canary credentials, and 1 draining ETH from a researcher-owned private key. Two poisoning studies further show that ostensibly benign routers can be pulled into the same attack surface: a leaked OpenAI key generates 100M GPT-5.4 tokens and more than seven Codex sessions, while weakly configured decoys yield 2B billed tokens, 99 credentials across 440 Codex sessions, and 401 sessions already running in autonomous YOLO mode. We build Mine, a research proxy that implements all four attack classes against four public agent frameworks, and use it to evaluate three deployable client-side defenses: a fail-closed policy gate, response-side anomaly screening, and append-only transparency logging.

The Model Context Protocol (MCP) enables large language models (LLMs) to dynamically discover and invoke third-party tools, significantly expanding agent capabilities while introducing a distinct security landscape. Unlike prompt-only interactions, MCP exposes pre-execution artifacts, shared context, multi-turn workflows, and third-party supply chains to adversarial influence across independently operated components. While recent work has identified MCP-specific attacks and evaluated defenses, existing studies are largely attack-centric or benchmark-driven, providing limited guidance on where mitigation responsibility should reside within the MCP architecture. This is problematic given MCP's multi-party design and distributed trust boundaries. We present a defense-placement-oriented security analysis of MCP, introducing a layer-aligned taxonomy that organizes attacks by the architectural component responsible for enforcement. Threats are mapped across six MCP layers, and primary and secondary defense points are identified to support principled defense-in-depth reasoning under adversaries controlling tools, servers, or ecosystem components. A structured mapping of existing academic and industry defenses onto this framework reveals uneven and predominantly tool-centric protection, with persistent gaps at the host orchestration, transport, and supply-chain layers. These findings suggest that many MCP security weaknesses stem from architectural misalignment rather than isolated implementation flaws.

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.

Large language models (LLMs) increasingly rely on external tools to perform time-sensitive tasks and real-world actions. While tool integration expands LLM capabilities, it also introduces a new prompt-injection attack surface: tool poisoning attacks (TPAs). Attackers manipulate tool descriptions by embedding malicious instructions (explicit TPAs) or misleading claims (implicit TPAs) to influence model behavior and tool selection. Existing defenses mainly detect anomalous instructions and remain ineffective against implicit TPAs. In this paper, we present TRUSTDESC, the first framework for preventing tool poisoning by automatically generating trusted tool descriptions from implementations. TRUSTDESC derives implementation-faithful descriptions through a three-stage pipeline. SliceMin performs reachability-aware static analysis and LLM-guided debloating to extract minimal tool-relevant code slices. DescGen synthesizes descriptions from these slices while mitigating misleading or adversarial code artifacts. DynVer refines descriptions through dynamic verification by executing synthesized tasks and validating behavioral claims. We evaluate TRUSTDESC on 52 real-world tools across multiple tool ecosystems. Results show that TRUSTDESC produces accurate tool descriptions that improve task completion rates while mitigating implicit TPAs at their root, with minimal time and monetary overhead.