Cover Image

Semia: Auditing Agent Skills via Constraint-Guided Representation Synthesis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wen, Hongbo, Li, Ying, Liu, Hanzhi, Shou, Chaofan, Chen, Yanju, Tian, Yuan, Feng, Yu
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence Programming Languages
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FORAY: Towards Effective Attack Synthesis against Deep Logical Vulnerabilities in DeFi Protocols
by: Wen, Hongbo, et al.
Published: (2024)

No Attack Required: Semantic Fuzzing for Specification Violations in Agent Skills
by: Li, Ying, et al.
Published: (2026)

Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain
by: Liu, Hanzhi, et al.
Published: (2026)

Synthesizing Multi-Agent Harnesses for Vulnerability Discovery
by: Liu, Hanzhi, et al.
Published: (2026)

Picachv: Formally Verified Data Use Policy Enforcement for Secure Data Analytics
by: Chen, Haobin Hiroki, et al.
Published: (2025)

Lightweight Yet Secure: Secure Scripting Language Generation via Lightweight LLMs
by: Zhang, Keyang, et al.
Published: (2026)

Constraint-Level Design of zkEVMs: Architectures, Trade-offs, and Evolution
by: Hassanzadeh-Nazarabadi, Yahya, et al.
Published: (2025)

Secure Synthesis of Distributed Cryptographic Applications (Technical Report)
by: Acay, Coşku, et al.
Published: (2024)

LockForge: Automating Paper-to-Code for Logic Locking with Multi-Agent Reasoning LLMs
by: Saha, Akashdeep, et al.
Published: (2025)

ILA: Correctness via Type Checking for Fully Homomorphic Encryption
by: Gollamudi, Tarakaram, et al.
Published: (2025)

Neuroforger: certified violation witnesses for smart contracts verification via LLMs
by: Bartoletti, Massimo, et al.
Published: (2026)

Synthesizing Tight Privacy and Accuracy Bounds via Weighted Model Counting
by: Oakley, Lisa, et al.
Published: (2024)

Automated Repair of OpenID Connect Programs (Extended Version)
by: Rahat, Tamjid Al, et al.
Published: (2025)

PAuth - Precise Task-Scoped Authorization For Agents
by: Sharma, Reshabh K, et al.
Published: (2026)

Theorem-Carrying Transactions: Runtime Verification to Ensure Interface Specifications for Smart Contract Safety
by: Ball, Thomas, et al.
Published: (2024)

Beyond Imprecise Distance Metrics: Trace-Guided Directed Greybox Fuzzing via LLM-Predicted Call Stacks
by: Zhang, Yifan, et al.
Published: (2025)

Deterministic Fully-Static Whole-Binary Translation without Heuristics
by: Chen, Hongyu, et al.
Published: (2026)

TYPEPULSE: Detecting Type Confusion Bugs in Rust Programs
by: Chen, Hung-Mao, et al.
Published: (2025)

Behavioral Canaries: Auditing Private Retrieved Context Usage in RL Fine-Tuning
by: Chen, Chaoran, et al.
Published: (2026)

Language-Based Agent Control
by: Zhou, Timothy, et al.
Published: (2026)

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

AC4A: Access Control for Agents
by: Sharma, Reshabh K, et al.
Published: (2026)

Hound: Relation-First Knowledge Graphs for Complex-System Reasoning in Security Audits
by: Mueller, Bernhard
Published: (2025)

PermRust: A Token-based Permission System for Rust
by: Gehring, Lukas, et al.
Published: (2025)

Nanopass Back-Translation of Call-Return Trees for Mechanized Secure Compilation Proofs
by: Thibault, Jérémy, et al.
Published: (2025)

FSLH: Flexible Mechanized Speculative Load Hardening
by: Baumann, Jonathan, et al.
Published: (2025)

Adding Compilation Metadata To Binaries To Make Disassembly Decidable
by: Engel, Daniel, et al.
Published: (2026)

Compositional security definitions for higher-order where declassification
by: Menz, Jan, et al.
Published: (2026)

OpenAPI Specification Extended Security Scheme: A method to reduce the prevalence of Broken Object Level Authorization
by: Haddad, Rami, et al.
Published: (2022)

Computationally Bounded Robust Compilation and Universally Composable Security
by: Künnemann, Robert, et al.
Published: (2024)

Obfuscation as Instruction Decorrelation
by: Ajorian, Ali, et al.
Published: (2024)

SNIP: Speculative Execution and Non-Interference Preservation for Compiler Transformations
by: van der Wall, Sören, et al.
Published: (2024)

Automated Repeatable Adversary Threat Emulation with Effects Language (EL)
by: Damodaran, Suresh K., et al.
Published: (2025)

Formalizing, Verifying and Applying ISA Security Guarantees as Universal Contracts
by: Huyghebaert, Sander, et al.
Published: (2023)

SplittingSecrets: A Compiler-Based Defense for Preventing Data Memory-Dependent Prefetcher Side-Channels
by: Sharma, Reshabh K, et al.
Published: (2026)

Smart Contract Languages: a comparative analysis
by: Bartoletti, Massimo, et al.
Published: (2024)

Censor Resistant Instruction Independent Obfuscation for Multiple Programs
by: Ajorian, Ali
Published: (2025)

On Computational Indistinguishability and Logical Relations
by: Lago, Ugo Dal, et al.
Published: (2024)

HasTEE+ : Confidential Cloud Computing and Analytics with Haskell
by: Sarkar, Abhiroop, et al.
Published: (2024)

A Bayesian Approach to Membership Inference for Statistical Release
by: Oakley, Lisa, et al.
Published: (2026)