Cover Image

Sealing the Audit-Runtime Gap for LLM Skills

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shen, Tingda, Feng, Yebo, Zhu, Konglin, Jia, Xiaojun, Liu, Yang, Zhang, Lin
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TRACES: TEE-based Runtime Auditing for Commodity Embedded Systems
by: Caulfield, Adam, et al.
Published: (2024)

Slot: Provenance-Driven APT Detection through Graph Reinforcement Learning
by: Qiao, Wei, et al.
Published: (2024)

Don't Trust Your Upstream: Exploiting LLM Multi-Agent System via Topology-Guided Adversarial Propagation
by: Liang, Ruichao, et al.
Published: (2025)

AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skills
by: Zhuang, Haomin, et al.
Published: (2026)

Benchmarking LLMs and LLM-based Agents in Practical Vulnerability Detection for Code Repositories
by: Yildiz, Alperen, et al.
Published: (2025)

SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents
by: Jia, Xiaojun, et al.
Published: (2026)

Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking
by: Zhang, Junke, et al.
Published: (2026)

JailGuard: A Universal Detection Framework for LLM Prompt-based Attacks
by: Zhang, Xiaoyu, et al.
Published: (2023)

SkillProbe: Security Auditing for Emerging Agent Skill Marketplaces via Multi-Agent Collaboration
by: Guo, Zihan, et al.
Published: (2026)

ContraFix: Agentic Vulnerability Repair via Differential Runtime Evidence and Skill Reuse
by: Liu, Simiao, et al.
Published: (2026)

LiquiLM: Bridging the Semantic Gap in Liquidity Flaw Audit via DCN and LLMs
by: Liu, Zekai, et al.
Published: (2026)

EBCC: Enclave-Backed Confidential Containers via OCI-Compatible Runtime Integration
by: Lu, Di, et al.
Published: (2026)

ProvX: Generating Counterfactual-Driven Attack Explanations for Provenance-Based Detection
by: Wu, Weiheng, et al.
Published: (2025)

Benchmarking ZK-Friendly Hash Functions and SNARK Proving Systems for EVM-compatible Blockchains
by: Guo, Hanze, et al.
Published: (2024)

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

Runtime Backdoor Detection for Federated Learning via Representational Dissimilarity Analysis
by: Zhang, Xiyue, et al.
Published: (2025)

Hidden You Malicious Goal Into Benign Narratives: Jailbreak Large Language Models through Logic Chain Injection
by: Wang, Zhilong, et al.
Published: (2024)

GoAT-X: A Graph of Auditing Thoughts for Securing Token Transactions in Cross-Chain Contracts
by: Feng, Zijun, et al.
Published: (2026)

iSeal: Encrypted Fingerprinting for Reliable LLM Ownership Verification
by: Xiong, Zixun, et al.
Published: (2025)

Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attacks
by: Shen, Huanming, et al.
Published: (2025)

Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study
by: Wang, Zihan, et al.
Published: (2026)

Semia: Auditing Agent Skills via Constraint-Guided Representation Synthesis
by: Wen, Hongbo, et al.
Published: (2026)

Synthetic Artifact Auditing: Tracing LLM-Generated Synthetic Data Usage in Downstream Applications
by: Wu, Yixin, et al.
Published: (2025)

Audit-LLM: Multi-Agent Collaboration for Log-based Insider Threat Detection
by: Song, Chengyu, et al.
Published: (2024)

SoK: Runtime Integrity
by: Ammar, Mahmoud, et al.
Published: (2024)

When Skills Lie: Hidden-Comment Injection in LLM Agents
by: Wang, Qianli, et al.
Published: (2026)

Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills
by: He, Wenhui, et al.
Published: (2026)

Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills
by: Lv, Lijia, et al.
Published: (2026)

HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?
by: Jiang, Yukun, et al.
Published: (2026)

Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling
by: Wang, Ziwei, et al.
Published: (2026)

CapSeal: Capability-Sealed Secret Mediation for Secure Agent Execution
by: Jin, Shutong, et al.
Published: (2026)

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run
by: Liu, Ruixuan, et al.
Published: (2025)

SnapAudit: Active Auditing of Differentially Private In-Context Learning via Snapshot-Based Simulation
by: Xia, Yuyang, et al.
Published: (2025)

Prompt Control-Flow Integrity: A Priority-Aware Runtime Defense Against Prompt Injection in LLM Systems
by: Alam, Md Takrim Ul, et al.
Published: (2026)

CODE: A Contradiction-Based Deliberation Extension Framework for Overthinking Attacks on Retrieval-Augmented Generation
by: Zhang, Xiaolei, et al.
Published: (2026)

SilentLedger: Privacy-Preserving Auditing for Blockchains with Complete Non-Interactivity
by: Liu, Zihan, et al.
Published: (2025)

Hermes Seal: Zero-Knowledge Assurance for Autonomous Vehicle Communications
by: Hasan, Munawar, et al.
Published: (2026)

Hedge Funds on a Swamp: Analyzing Patterns, Vulnerabilities, and Defense Measures in Blockchain Bridges
by: Azad, Poupak, et al.
Published: (2025)

SmmPack: Obfuscation for SMM Modules with TPM Sealed Key
by: Matsuo, Kazuki, et al.
Published: (2024)

DataSeal: Ensuring the Verifiability of Private Computation on Encrypted Data
by: Santriaji, Muhammad Husni, et al.
Published: (2024)