# HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?

arXiv: https://arxiv.org/abs/2604.15415 · HTML: https://mlsanity.com/paper/2604.15415/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 41 of its 70 references that are in the map.
- First posted on arXiv 16 Apr 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, 30 of 41)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (2023)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents](https://mlsanity.com/paper/2403.02691/) (2024)
- [JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](https://mlsanity.com/paper/2404.01318/) (2024)
- ["Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models](https://mlsanity.com/paper/2308.03825/) (2023)
- [Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation](https://mlsanity.com/paper/2310.06987/) (2023)
- [AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents](https://mlsanity.com/paper/2410.09024/) (2024)
- [AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases](https://mlsanity.com/paper/2407.12784/) (2024)
- [A StrongREJECT for Empty Jailbreaks](https://mlsanity.com/paper/2402.10260/) (2024)
- [Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents](https://mlsanity.com/paper/2410.02644/) (2024)
- [Agent-SafetyBench: Evaluating the Safety of LLM Agents](https://mlsanity.com/paper/2412.14470/) (2024)
- [R-Judge: Benchmarking Safety Risk Awareness for LLM Agents](https://mlsanity.com/paper/2401.10019/) (2024)
- [ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving](https://mlsanity.com/paper/2309.17452/) (2023)
- [EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage](https://mlsanity.com/paper/2409.11295/) (2024)
- [AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents](https://mlsanity.com/paper/2406.13352/) (2024)
- [Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents](https://mlsanity.com/paper/2402.11208/) (2024)
- [BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents](https://mlsanity.com/paper/2406.03007/) (2024)
- [Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward](https://mlsanity.com/paper/2602.12430/) (2026)
- [JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs](https://mlsanity.com/paper/2402.05668/) (2024)
- [Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality](https://mlsanity.com/paper/2602.08004/) (2026)
- [Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale](https://mlsanity.com/paper/2603.02176/) (2026)
- [Imprompter: Tricking LLM Agents into Improper Tool Use](https://mlsanity.com/paper/2410.14923/) (2024)
- [Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injection](https://mlsanity.com/paper/2308.10819/) (2023)
- [LLM Platform Security: Applying a Systematic Evaluation Framework to OpenAI's ChatGPT Plugins](https://mlsanity.com/paper/2309.10254/) (2023)

## Built on by (most cited first, 11 of 11)

- [Benign in Isolation, Harmful in Composition: Security Risks in Agent Skill Ecosystems](https://mlsanity.com/paper/2606.15242/) (2026)
- [AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skills](https://mlsanity.com/paper/2605.13940/) (2026)
- [VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills](https://mlsanity.com/paper/2606.26524/) (2026)
- [Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries](https://mlsanity.com/paper/2607.10113/) (2026)
- [JailbreakSkill: Scaling Automated Red-Teaming with Reusable and Ever-Evolving Skills](https://mlsanity.com/paper/2608.16465/) (2026)
- [Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models](https://mlsanity.com/paper/2606.12203/) (2026)
- [ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents](https://mlsanity.com/paper/2608.09476/) (2026)
- [Towards a Systems Foundation for Agentic Skills: Architecture, Lifecycle, and Security](https://mlsanity.com/paper/2608.29596/) (2026)
- [MMSkillRisk: Can Agents Stay Safe When Multimodal Skills Become Traps?](https://mlsanity.com/paper/2609.35912/) (2026)
- [SKILLLITE: Evidence-Guided Malicious Skill Auditing with Compact LLMs](https://mlsanity.com/paper/2609.36879/) (2026)
- [Why Static Skill Inconsistencies Do Not Equate to Runtime Risks: A Behavioral Analysis of LLM Agent Execution](https://mlsanity.com/paper/2610.18927/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have evolved into autonomous agents that rely on open skill ecosystems (e.g., ClawHub and Skills.Rest), hosting numerous publicly reusable skills. Existing security research on these ecosystems mainly focuses on vulnerabilities within skills, such as prompt injection. However, there is a critical gap regarding skills that may be misused for harmful actions (e.g., cyber attacks, fraud and scams, privacy violations, and sexual content generation), namely harmful skills. In this paper, we present the first large-scale measurement study of harmful skills in agent ecosystems, covering 98,440 skills across two major registries. Using an LLM-driven scoring system grounded in our harmful skill taxonomy, we find that 4.93% of skills (4,858) are harmful, with ClawHub exhibiting an 8.84% harmful rate compared to 3.49% on Skills.Rest. We then construct HarmfulSkillBench, the first benchmark for evaluating agent safety against harmful skills in realistic agent contexts, comprising 200 harmful skills across 20 categories and four evaluation conditions. By evaluating six LLMs on HarmfulSkillBench, we find that presenting a harmful task through a pre-installed skill substantially lowers refusal rates across all models, with the average harm score rising from 0.27 without the skill to 0.47 with it, and further to 0.76 when the harmful intent is implicit rather than stated as an explicit user request. We responsibly disclose our findings to the affected registries and release our benchmark to support future research (see https://github.com/TrustAIRLab/HarmfulSkillBench).