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

arXiv: https://arxiv.org/abs/2608.03485 · HTML: https://mlsanity.com/paper/2608.03485/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 28 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 13 of 13)

- [Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents](https://mlsanity.com/paper/2410.02644/) (2024)
- [ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities](https://mlsanity.com/paper/2408.04682/) (2024)
- [R-Judge: Benchmarking Safety Risk Awareness for LLM Agents](https://mlsanity.com/paper/2401.10019/) (2024)
- [Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks](https://mlsanity.com/paper/2602.20156/) (2026)
- ["Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild](https://mlsanity.com/paper/2602.06547/) (2026)
- [SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents](https://mlsanity.com/paper/2602.14211/) (2026)
- [MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills](https://mlsanity.com/paper/2606.07131/) (2026)
- [Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry](https://mlsanity.com/paper/2605.11418/) (2026)
- [Detecting Malicious Agent Skills in the Wild using Attention](https://mlsanity.com/paper/2606.23416/) (2026)
- [Poise: Position-Aware One-Instruction Skill Injection for Silent Execution on LLM Agents](https://mlsanity.com/paper/2606.07943/) (2026)
- [Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification](https://mlsanity.com/paper/2607.01793/) (2026)
- [PhantomSkill: Malicious Code Injection in Agent Skill Ecosystems](https://mlsanity.com/paper/2606.19191/) (2026)
- [SkillMutator: Benchmarking and Defending Language-and-Code Cross-modal Attacks on LLM Agent Skills](https://mlsanity.com/paper/2606.14154/) (2026)

## Abstract (arXiv)

External skills extend the capabilities of large language model agents, but also introduce an execution-time attack surface: a skill that appears benign under inspection may reveal harmful behavior only after particular environmental states, resources, or interaction histories are encountered. Existing scanners primarily rely on static analysis, predefined rules, or one-shot semantic judgments, making such conditional behavior difficult to elicit and attribute. We present SkillSentry, a dynamic safety-testing framework based on adaptive honey worlds. SkillSentry infers the intended capability boundary of a skill, constructs an LLM-simulated environment with controlled decoy resources, and adaptively generates tasks to explore its behavioral states. It then compares skill-enabled trajectories with matched no-skill executions, grounding suspicious behaviors in source code and verified execution traces before making a final decision. We evaluate SkillSentry against seven scanner configurations. SkillSentry achieves 99.50% Recall and 96.26% average F1 on standard benchmarks. Under semantics-preserving evasion, it reaches 92.95% average F1, compared with 80.07% for the strongest baselines. Our code is available at https://github.com/nizhangli062-jpg/SkillSentry-Adaptive-Honey-Worlds-for-Dynamic-Safety-Testing-of-Agent-Skills.