SkillMutator: Benchmarking and Defending Language-and-Code Cross-modal Attacks on LLM Agent Skills

• URL: http://arxiv.org/abs/2606.14154v1
• Date: Fri, 12 Jun 2026 06:27:12 GMT
• Title: SkillMutator: Benchmarking and Defending Language-and-Code Cross-modal Attacks on LLM Agent Skills
• Abstract summary: Large language model (LLM) agents increasingly extend their capabilities at runtime by loading Agent Skills.<n>Because a skill's behavior relies on both natural-language instructions and executable code, assessing its safety requires cross-modal reasoning.<n>We introduce SkillMutator, the first benchmark for install-time detection of language-and-code cross-modal attacks on Agent Skills.
• Score: 7.465256215885481
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language model (LLM) agents increasingly extend their capabilities at runtime by loading Agent Skills, which pair natural-language specifications (SKILL.md) with executable scripts and resources. Because a skill's behavior relies on both natural-language instructions and executable code, assessing its safety requires cross-modal reasoning, creating a new language-and-code attack surface. Attackers can present a benign workflow in SKILL.md while embedding implicit directives that steer the agent to exfiltrate sensitive files, even if the scripts appear harmless. This attack surface remains understudied; prior work treats skills merely as prompt-injection vectors or static code artifacts, leaving attacks emerging from cross-modal interactions largely unmeasured. In our evaluation, open-source and commercial skill scanners detect only 2%-8% and 9%-17% of such attacks, respectively. To address this gap, we introduce SkillMutator, the first benchmark for install-time detection of language-and-code cross-modal attacks on Agent Skills. It emulates an adversarial mutation process across 13 attack categories, iteratively refining malicious skills using scanner feedback to make injected behaviors indistinguishable from legitimate workflows. We further propose a four-phase reasoning-trajectory distillation framework to distill frontier-teacher traces into smaller open-weight models. This produces a locally deployable scanner avoiding third-party data exposure and excessive API costs. On the strongest SkillMutator subset (n=76), our distilled model (Qwen2.5-Coder-7B-Instruct) improves detection from 17.1% to 88.2%, surpassing GPT-4o-mini (23.7%) and GPT-5.4-mini (79.0%), and reaching frontier-level GPT-5.4 (86.8%). These results show practical defense against cross-modal attacks is feasible without relying on costly frontier models.

Related papers

• Towards a Risk Assessment of Malicious Skill Files in Coding Agents [9.553517006800913]
  We make three contributions to the field of autonomous coding agents.<n>First, an adversarial skill-synthesis method to transform 471 real-world shell commands into benign-appearing skills.<n>Second, a reproducible evaluation pipeline coupling run stratification, evidence anchoring, a refusal veto, and a deterministic declared-intent override.<n>Third, a large-scale characterization of two enterprise-grade agents across 5,629 completed runs.
  arXiv  Detail & Related papers  (2026-08-05T11:33:43Z)
• Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malware [15.064889350201511]
  Malicious skills can steal credentials, exfiltrate source code, or install backdoors.<n> Existing defenses use pattern matching or LLM-as-judge analysis.<n>We propose SkillDetonate, a behavior-centric auditor that executes skills in a sandbox.
  arXiv  Detail & Related papers  (2026-07-02T16:00:52Z)
• SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction [89.03272793385054]
  Agent skills occupy a privileged position in the agent workflow, rendering third-party skills a vulnerable attack surface.<n>We introduce SkillHarm, a benchmark of skill-based attacks across the skill-use lifecycle.<n>We show that current agents remain vulnerable with attack success rates up to 86.3% in FPP and 69.3% in SMP.
  arXiv  Detail & Related papers  (2026-06-01T17:45:39Z)
• Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry [49.83108591873481]
  We study SKILL.md - only attacks across three registry-facing stages of the Agent Skill lifecycle.<n>We show that SKILL.md is not passive documentation but operational text that shapes which third-party capabilities agents find, trust, and use.
  arXiv  Detail & Related papers  (2026-05-12T02:11:54Z)
• BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning [34.60596020541521]
  We present BadSkill, a backdoor attack formulation that targets model-in-skill threat surface.<n>In BadSkill, an adversary publishes a seemingly benign skill whose embedded model is backdoor-fine-tuned to activate a hidden payload.<n>Our benchmark spans 13 skills, including 8 triggered tasks and 5 non-trigger control skills, with a combined main evaluation set of 571 negative-class queries and 396 trigger-aligned queries.<n>BadSkill achieves up to 99.5% average attack success rate (ASR) across the eight triggered skills while maintaining strong benign-side accuracy on negative-class queries.
  arXiv  Detail & Related papers  (2026-04-10T14:48:29Z)
• Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems [35.65937852381774]
  Document-Driven Implicit Payload Execution (DDIPE) embeds malicious logic in code examples and configuration templates within skill documentation.<n>We generate 1,070 adversarial skills from 81 seeds across 15 MITRE ATTACK categories.<n>DDIPE achieves 11.6% to 33.5% bypass rates, while explicit instruction attacks achieve 0% under strong defenses.
  arXiv  Detail & Related papers  (2026-04-03T14:58:58Z)
• Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks [27.120130204872325]
  We introduce SkillInject, a benchmark evaluating the susceptibility of widely-used LLM agents to injections through skill files.<n>SkillInject contains 202 injection-task pairs with attacks ranging from obviously malicious injections to subtle, context-dependent attacks hidden in otherwise legitimate instructions.<n>Our results show that today's agents are highly vulnerable with up to 80% attack success rate with frontier models.
  arXiv  Detail & Related papers  (2026-02-23T18:59:27Z)
• SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement [120.52289344734415]
  We propose an automated framework for stealthy prompt injection tailored to agent skills.<n>The framework forms a closed loop with three agents: an Attack Agent that synthesizes injection skills under explicit stealth constraints, a Code Agent that executes tasks using the injected skills and an Evaluate Agent that logs action traces.<n>Our method consistently achieves high attack success rates under realistic settings.
  arXiv  Detail & Related papers  (2026-02-15T16:09:48Z)
• AI Security Beyond Core Domains: Resume Screening as a Case Study of Adversarial Vulnerabilities in Specialized LLM Applications [71.27518152526686]
  Large Language Models (LLMs) excel at text comprehension and generation, making them ideal for automated tasks like code review and content moderation.<n>LLMs can be manipulated by "adversarial instructions" hidden in input data, such as resumes or code, causing them to deviate from their intended task.<n>This paper introduces a benchmark to assess this vulnerability in resume screening, revealing attack success rates exceeding 80% for certain attack types.
  arXiv  Detail & Related papers  (2025-12-23T08:42:09Z)
• AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents [54.29555239363013]
  We propose a generic black-box fuzzing framework, AgentVigil, to automatically discover and exploit indirect prompt injection vulnerabilities.<n>We evaluate AgentVigil on two public benchmarks, AgentDojo and VWA-adv, where it achieves 71% and 70% success rates against agents based on o3-mini and GPT-4o.<n>We apply our attacks in real-world environments, successfully misleading agents to navigate to arbitrary URLs, including malicious sites.
  arXiv  Detail & Related papers  (2025-05-09T07:40:17Z)
• Dissecting Adversarial Robustness of Multimodal LM Agents [70.2077308846307]
  We manually create 200 targeted adversarial tasks and evaluation scripts in a realistic threat model on top of VisualWebArena.<n>We find that we can successfully break latest agents that use black-box frontier LMs, including those that perform reflection and tree search.<n>We also use ARE to rigorously evaluate how the robustness changes as new components are added.
  arXiv  Detail & Related papers  (2024-06-18T17:32:48Z)
• TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning [63.481446315733145]
  Cross-lingual backdoor attacks against multilingual large language models (LLMs) are under-explored.<n>Our research focuses on how poisoning the instruction-tuning data for one or two languages can affect the outputs for languages whose instruction-tuning data were not poisoned.<n>Our method exhibits remarkable efficacy in models like mT5 and GPT-4o, with high attack success rates, surpassing 90% in more than 7 out of 12 languages.
  arXiv  Detail & Related papers  (2024-04-30T14:43:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.