ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners

• URL: http://arxiv.org/abs/2608.09732v1
• Date: Mon, 10 Aug 2026 15:32:44 GMT
• Title: ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners
• Abstract summary: Agent skills are emerging as an important attack surface in LLM-based agent systems.<n>Current defenses mainly inspect individual skills, leaving risks from cross-skill composition insufficiently examined.<n>We propose ColluSkill, a collusive multi-skill-chain attack framework that decomposes a complete malicious intent into interdependent sub-payloads.
• Score: 23.03858552822385
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agent skills are emerging as an important attack surface in LLM-based agent systems. Through an empirical study of existing skill scanners, we find that current defenses mainly inspect individual skills, leaving risks from cross-skill composition insufficiently examined. This creates a practical blind spot: multiple locally plausible skills may pass security checks while collectively forming a harmful workflow during agent execution. To investigate this threat, we propose ColluSkill, a collusive multi-skill-chain attack framework that decomposes a complete malicious intent into interdependent sub-payloads embedded in independently packaged skills. The attack does not rely on any single malicious skill, but emerges from the ordered composition of locally plausible behaviors through contextual dependencies, artifact passing, and execution handoffs. ColluSkill further employs LLM-based chain planning and scanner-feedback refinement to preserve chain-level attack semantics while reducing suspicious signals in individual sub-skills. To defend against such attacks, we propose ChainGuard, a context-aware skill-chain scanner that jointly analyzes a candidate skill and the skills already installed in the agent environment. ChainGuard reconstructs cross-skill dependencies, artifact flows, capability compositions, and downstream behaviors to identify risks that emerge only at the workflow level. Experiments on six representative skill scanners show that ColluSkill achieves an average attack success rate of 96.0% and consistently outperforms the evaluated single-skill and multi-skill attack baselines. Meanwhile, ChainGuard reduces the attack success rate to 22.5% while allowing 99.5% of benign workflows to pass, highlighting the importance of chain-level security analysis for agent skill ecosystems.

Related papers

• AgentLeak: Cloning Stronger LLM Agent Capabilities onto Weaker Agents Beyond Skill Stealing [18.52239289354215]
  We show that a weaker agent may possess the same skills but still fail because it lacks procedural behaviors implicitly realized by the stronger agent.<n>Our key insight is that the skill execution gap itself forms a leakage surface, where missing behaviors are exposed.<n>We present AgentLeak, a black-box capability-cloning attack that identifies capability-critical behaviors from these execution differences and incorporates them into attacker-side skills.
  arXiv  Detail & Related papers  (2026-09-07T07:30:02Z)
• CompoSkill: Compositional Skill Chain Attacks from Individually Scanner-Passing LLM Agent Skills [11.454357977708389]
  We show that autonomous AI agents tackling Long Horizon Tasks depend on marketplace skills that are certified one at a time.<n>A skill may pass the per-skill scanner individually yet participate in a risky composition when an agent connects its outputs, capabilities, or side effects with those of other scanner-passing skills.<n>We present CompoSkill, a framework that constructs skill composition attacks through a dual attacker system.
  arXiv  Detail & Related papers  (2026-08-17T08:20:44Z)
• 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)
• 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)
• SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement [66.44008181092832]
  LLM-based agent systems increasingly rely on agent skills sourced from open registries to extend their capabilities.<n>We introduce SkillAttack, a framework that verifies skill vulnerability exploitability through adversarial prompting.
  arXiv  Detail & Related papers  (2026-04-05T06:25:11Z)
• SkillProbe: Security Auditing for Emerging Agent Skill Marketplaces via Multi-Agent Collaboration [22.680481305584028]
  SkillProbe is a multi-stage security auditing framework driven by multi-agent collaboration.<n>We conducted a large-scale evaluation using 8 mainstream series across 2,500 real-world skills from ClawHub.<n>Our results reveal a striking popularity-security paradox, where download volume is not a reliable proxy security quality.
  arXiv  Detail & Related papers  (2026-03-22T02:31:27Z)
• Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain [82.98626829232899]
  Fine-tuning AI agents on data from their own interactions introduces a critical security vulnerability within the AI supply chain.<n>We show that adversaries can easily poison the data collection pipeline to embed hard-to-detect backdoors.
  arXiv  Detail & Related papers  (2025-10-03T12:47:21Z)
• AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning [78.5751183537704]
  AdvEvo-MARL is a co-evolutionary multi-agent reinforcement learning framework that internalizes safety into task agents.<n>Rather than relying on external guards, AdvEvo-MARL jointly optimize attackers and defenders.
  arXiv  Detail & Related papers  (2025-10-02T02:06:30Z)
• BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks [58.959622170433725]
  BlindGuard is an unsupervised defense method that learns without requiring any attack-specific labels or prior knowledge of malicious behaviors.<n>We show that BlindGuard effectively detects diverse attack types (i.e., prompt injection, memory poisoning, and tool attack) across multi-agent systems.
  arXiv  Detail & Related papers  (2025-08-11T16:04:47Z)
• Learning and Certification under Instance-targeted Poisoning [49.55596073963654]
  We study PAC learnability and certification under instance-targeted poisoning attacks. We show that when the budget of the adversary scales sublinearly with the sample complexity, PAC learnability and certification are achievable. We empirically study the robustness of K nearest neighbour, logistic regression, multi-layer perceptron, and convolutional neural network on real data sets.
  arXiv  Detail & Related papers  (2021-05-18T17:48:15Z)

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.