SkillSentry: Adaptive Honey Worlds for Dynamic Safety Testing of Agent Skills

arXiv:2608.03485 · cs.CR · Submitted 2026-08-04 · Read on arXiv

Nizhang Li, Zonghao Ying, Xiangfan Wu, Zonglei Jing, Xixun Lin, Hao Zhang, Wenxin Zhang, Jiaye Lin, Quanchen Zou, Xiangzheng Zhang

cs.CR

Submitted: 2026-08-04

Code: https://github.com/nizhangli062-jpg/SkillSentry-Adaptive-Honey-Worlds-for-Dynamic-Safety-Testing-of-Agent-Skills

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 27× in this paper · explained in 2 episodes
• Trace — 10× in this paper · explained in 2 episodes
• Generator — 8× in this paper · explained in 2 episodes
• Verification — 5× in this paper · explained in 2 episodes
• Verifier — 5× in this paper · explained in 2 episodes
• Benchmarking — 4× in this paper · explained in 4 episodes
• Grounding — 4× in this paper · explained in 3 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Robustness — 2× in this paper · explained in 6 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• F1 Score — 1× in this paper · explained in 4 episodes
• Indirect Prompt Injection — 1× in this paper · explained in 2 episodes
• Prompt Injection Attacks — 1× in this paper · explained in 2 episodes
• Task Alignment — 1× in this paper · explained in 2 episodes

Sources

• Detecting Malicious Agent Skills in the Wild using Attention
• Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification
• MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills
• One Skill, Two Masters: Serving Users and Attackers through Skill Injection
• Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malware
• SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents
• HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?
• SkillMutator: Benchmarking and Defending Language-and-Code Cross-modal Attacks on LLM Agent Skills
• Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis
• PhantomSkill: Malicious Code Injection in Agent Skill Ecosystems
• "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild
• Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry
• Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Estimating the Social Cost of Corporate Data Breaches
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills