Copertina

AEGIS: No Tool Call Left Unchecked -- A Pre-Execution Firewall and Audit Layer for AI Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yuan, Aojie, Su, Zhiyuan, Zhao, Yue
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

UEChecker: Detecting Unchecked External Call Vulnerabilities in DApps via Graph Analysis
di: Kong, Dechao, et al.
Pubblicazione: (2025)

Sovereign-OS: A Charter-Governed Operating System for Autonomous AI Agents with Verifiable Fiscal Discipline
di: Yuan, Aojie, et al.
Pubblicazione: (2026)

Before the Tool Call: Deterministic Pre-Action Authorization for Autonomous AI Agents
di: Uchibeke, Uchi
Pubblicazione: (2026)

Adaptive Plan-Execute Framework for Smart Contract Security Auditing
di: Wei, Zhiyuan, et al.
Pubblicazione: (2025)

Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety
di: Chen, Xuan, et al.
Pubblicazione: (2026)

Enforcing Benign Trajectories: A Behavioral Firewall for Structured-Workflow AI Agents
di: Dang, Hung
Pubblicazione: (2026)

Agent Audit: A Security Analysis System for LLM Agent Applications
di: Zhang, Haiyue, et al.
Pubblicazione: (2026)

AI-Driven Dynamic Firewall Optimization Using Reinforcement Learning for Anomaly Detection and Prevention
di: Ahmad, Taimoor
Pubblicazione: (2025)

Securing Generative AI Agentic Workflows: Risks, Mitigation, and a Proposed Firewall Architecture
di: Bahadur, Sunil Kumar Jang, et al.
Pubblicazione: (2025)

AEGIS: From Clues to Verdicts -- Graph-Guided Deep Vulnerability Reasoning via Dialectics and Meta-Auditing
di: Fang, Sen, et al.
Pubblicazione: (2026)

Security Risks in Tool-Enabled AI Agents: A Systematic Analysis of Privileged Execution Environments
di: Goel, Hardik
Pubblicazione: (2026)

WAFFLED: Exploiting Parsing Discrepancies to Bypass Web Application Firewalls
di: Akhavani, Seyed Ali, et al.
Pubblicazione: (2025)

LlamaFirewall: An open source guardrail system for building secure AI agents
di: Chennabasappa, Sahana, et al.
Pubblicazione: (2025)

Indirect Prompt Injections: Are Firewalls All You Need, or Stronger Benchmarks?
di: Bhagwatkar, Rishika, et al.
Pubblicazione: (2025)

Introducing the Generative Application Firewall (GAF)
di: Farreny, Joan Vendrell, et al.
Pubblicazione: (2026)

The Cognitive Firewall:Securing Browser Based AI Agents Against Indirect Prompt Injection Via Hybrid Edge Cloud Defense
di: Lan, Qianlong, et al.
Pubblicazione: (2026)

Advancing Obfuscation Strategies to Counter China's Great Firewall: A Technical and Policy Perspective
di: Li, Li
Pubblicazione: (2025)

MiniScope: A Least Privilege Framework for Authorizing Tool Calling Agents
di: Zhu, Jinhao, et al.
Pubblicazione: (2025)

Causality Laundering: Denial-Feedback Leakage in Tool-Calling LLM Agents
di: Chinaei, Mohammad Hossein
Pubblicazione: (2026)

Firewall Regulatory Networks for Autonomous Cyber Defense
di: Duan, Qi, et al.
Pubblicazione: (2025)

Firewalls to Secure Dynamic LLM Agentic Networks
di: Abdelnabi, Sahar, et al.
Pubblicazione: (2025)

From Threat Intelligence to Firewall Rules: Semantic Relations in Hybrid AI Agent and Expert System Architectures
di: Bonfanti, Chiara, et al.
Pubblicazione: (2026)

TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models
di: Guo, Zhen, et al.
Pubblicazione: (2026)

AudAgent: Automated Auditing of Privacy Policy Compliance in AI Agents
di: Zheng, Ye, et al.
Pubblicazione: (2025)

Ghost Tool Calls: Issue-Time Privacy for Speculative Agent Tools
di: Mohammadi, Bardia, et al.
Pubblicazione: (2026)

ControlNET: A Firewall for RAG-based LLM System
di: Yao, Hongwei, et al.
Pubblicazione: (2025)

Clawdrain: Exploiting Tool-Calling Chains for Stealthy Token Exhaustion in OpenClaw Agents
di: Dong, Ben, et al.
Pubblicazione: (2026)

LLM-SmartAudit: Advanced Smart Contract Vulnerability Detection
di: Wei, Zhiyuan, et al.
Pubblicazione: (2024)

LIFT: Automating Symbolic Execution Optimization with Large Language Models for AI Networks
di: Wang, Ruoxi, et al.
Pubblicazione: (2025)

Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments
di: Schnabl, Christoph, et al.
Pubblicazione: (2025)

Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents
di: Zhou, Kaiyu, et al.
Pubblicazione: (2026)

OpenClaw PRISM: A Zero-Fork, Defense-in-Depth Runtime Security Layer for Tool-Augmented LLM Agents
di: Li, Frank
Pubblicazione: (2026)

Prompt Injection Attack to Tool Selection in LLM Agents
di: Shi, Jiawen, et al.
Pubblicazione: (2025)

FTSmartAudit: A Knowledge Distillation-Enhanced Framework for Automated Smart Contract Auditing Using Fine-Tuned LLMs
di: Wei, Zhiyuan, et al.
Pubblicazione: (2024)

AgentDID: Trustless Identity Authentication for AI Agents
di: Xu, Minghui, et al.
Pubblicazione: (2026)

Securing LLM Agents Need Intent-to-Execution Integrity
di: Qu, Wenjie, et al.
Pubblicazione: (2026)

Adaptive Cybersecurity: Dynamically Retrainable Firewalls for Real-Time Network Protection
di: Ahmadi, Sina
Pubblicazione: (2025)

Tight Privacy Audit in One Run
di: Xiang, Zihang, et al.
Pubblicazione: (2025)

Governing Dynamic Capabilities: Cryptographic Binding and Reproducibility Verification for AI Agent Tool Use
di: Zhou, Ziling
Pubblicazione: (2026)

MalTool: Malicious Tool Attacks on LLM Agents
di: Hu, Yuepeng, et al.
Pubblicazione: (2026)