SkillClone: Multi-Modal Clone Detection and Clone Propagation Analysis in the Agent Skill Ecosystem

• URL: http://arxiv.org/abs/2603.22447v1
• Date: Mon, 23 Mar 2026 18:17:17 GMT
• Title: SkillClone: Multi-Modal Clone Detection and Clone Propagation Analysis in the Agent Skill Ecosystem
• Abstract summary: We present SkillClone, the first multi-modal clone detection approach for agent skills.<n>On SkillClone-Bench, SkillClone achieves F1 of 0.939 with precision 0.952, outperforming flat TF-IDF.<n>Applying SkillClone to 20K skills reveals 258K clone pairs involving 75% of all skills, with 40% crossing author boundaries.
• Score: 16.221297353469957
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agent skills are modular instruction packages that combine YAML metadata, natural language instructions, and embedded code, and they have reached 196K publicly available instances, yet no mechanism exists to detect clone relationships among them. This gap creates systemic risks: a vulnerability in a widely copied skill silently persists across derivatives with no alert to maintainers. Existing clone detectors, designed for single-modality source code, cannot handle the multi-modal structure of skills, where clone evidence is distributed across three interleaved content channels. We present SkillClone, the first multi-modal clone detection approach for agent skills. SkillClone fuses flat TF-IDF similarity with per-channel decomposition (YAML, NL, code) through logistic regression, combining strong detection with interpretable type classification. We construct SkillClone-Bench, a balanced benchmark of 300 ground-truth pairs with stratified difficulty. On SkillClone-Bench, SkillClone achieves F1 of 0.939 with precision 0.952, outperforming flat TF-IDF (F1 = 0.881) and achieving 4.2x higher Type-4 (semantic) recall than MinHash. Applying SkillClone to 20K skills reveals 258K clone pairs involving 75% of all skills, with 40% crossing author boundaries. A deduplication analysis shows the ecosystem is inflated 3.5x: only 5,642 unique skill concepts underlie the 20K listed skills, and 41% of skills in clone families are superseded by a strictly better variant.

Related papers

• Demystifying Agent Skills: Why They Work-Until They Don't [58.92875630998418]
  Existing evaluations largely measure whether skills improve aggregated task success, leaving a more fundamental question underexplored: emphtextbfWhen do skills help, why do they work, and where do they fail?<n>We isolate the effects of representation, outcome annotation, retrieval difficulty, and cross-framework of skills.<n>We consolidate these observations into a taxonomy of three high-level categories and twelve skill-use modes.
  arXiv  Detail & Related papers  (2026-08-14T07:26:38Z)
• Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning [72.09826781730662]
  Long-horizon reasoning demands that the model switch between distinct skills inside a reasoning chain.<n>We introduce Skill Entropy, a measure of the difficulty of switching from one skill to another.<n>We propose Skill-Entropy RL, an RL framework where the model predicts not only the answer at each step but also the skill used to produce it.
  arXiv  Detail & Related papers  (2026-08-05T17:57:16Z)
• A Unified Model for Cross-Domain Clone Detection via Model Merging [9.757638656919832]
  Current deep learning detectors degrade significantly outside their training distribution.<n>We investigate model merging, a family of post-hoc techniques that operate solely on trained checkpoints.<n>Same-base TIES merging creates effective cross-domain detectors, validated across two model families and three random seeds.
  arXiv  Detail & Related papers  (2026-08-04T20:32:28Z)
• Generative Skill Composition for LLM Agents [58.47191648555256]
  LLM agents benefit from skills for solving complex tasks.<n>As skill libraries grow, selecting an appropriate skill composition has emerged as a central bottleneck.<n>We propose SkillComposer, which instantiates structured skill composition as task-conditioned skill sequence prediction.
  arXiv  Detail & Related papers  (2026-06-30T17:53:09Z)
• SkillMutator: Benchmarking and Defending Language-and-Code Cross-modal Attacks on LLM Agent Skills [7.465256215885481]
  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.
  arXiv  Detail & Related papers  (2026-06-12T06:27:12Z)
• Behavioral Integrity Verification for AI Agent Skills [9.127363793428119]
  We formalize this as the behavioral integrity verification (BIV) problem.<n>On 49,943 skills from the OpenClaw registry, the deviation taxonomy reveals a pervasive description-implementation gap.<n>On a 906-skill malicious-skill detection benchmark, BIV reaches an F1 of 0.946, outperforming state-of-the-art rule-based and single-pass LLM baselines.
  arXiv  Detail & Related papers  (2026-05-12T08:41:09Z)
• SkillEvolver: Skill Learning as a Meta-Skill [46.52001686198623]
  We propose textbfSkillEvolver, a lightweight, plug-and-play solution for online skill learning.<n>The learning target of SkillEvolver is the skill's prose and code, not model weights.<n>Unlike trace-distillation, the meta-skill refines only after deploying the learnt skill.
  arXiv  Detail & Related papers  (2026-05-11T12:58:25Z)
• SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills [0.0]
  SkillSieve is a three-layer detection framework that applies progressively deeper analysis only where needed.<n>On a 400-skill labeled benchmark, SkillSieve achieves 0.800 F1, outperforming ClawVet's 0.421, at an average cost of 0.006 per skill.
  arXiv  Detail & Related papers  (2026-04-08T00:58:48Z)
• Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study [51.717224133855886]
  Third-party skills extend LLM agents with powerful capabilities but often handle sensitive credentials in privileged environments.<n>We analyze 17,022 skills (sampled from 170,226 on SkillsMP) using static analysis, sandbox testing, and manual inspection.<n>We identify 520 vulnerable skills with 1,708 issues and derive a taxonomy of 10 leakage patterns (4 accidental and 6 adversarial)
  arXiv  Detail & Related papers  (2026-04-03T14:50:16Z)
• EvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification [85.3692584167951]
  Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks.<n>A tool is a single, self-contained function, whereas a skill is a structured bundle of interdependent multi-file artifacts.<n>EvoSkills is a self-evolving skills framework that enables agents to autonomously construct complex, multi-file skill packages.
  arXiv  Detail & Related papers  (2026-04-02T06:43:20Z)
• Formal Analysis and Supply Chain Security for Agentic AI Skills [0.0]
  SkillFortify is the first formal analysis framework for agent skill supply chains.<n>It provides a sound static analysis framework grounded in abstract interpretation.<n>It achieves 100% precision and 0% false positive rate on 540 skills, while SAT-based resolution handles 1,000-node graphs in under 100 ms.
  arXiv  Detail & Related papers  (2026-02-27T06:21:53Z)
• SkillNet: Create, Evaluate, and Connect AI Skills [159.47504178122156]
  SkillNet is an open infrastructure designed to create, evaluate, and organize AI skills at scale.<n>Our infrastructure integrates a repository of over 200,000 skills, an interactive platform, and a versatile Python toolkit.
  arXiv  Detail & Related papers  (2026-02-26T14:24:02Z)
• SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks [61.89812116484928]
  Agent Skills are structured packages of procedural knowledge that augment LLM agents at inference time.<n>We present SkillsBench, a benchmark of 86 tasks across 11 domains paired with curated Skills and deterministic verifiers.<n>We show curated Skills raise average pass rate by 16.2 percentage points(pp), but effects vary widely by domain.<n>Self-generated Skills provide no benefit on average, showing that models cannot reliably author the procedural knowledge they benefit from consuming.
  arXiv  Detail & Related papers  (2026-02-13T07:06:06Z)
• Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale [26.757365536859453]
  The rise of AI agent frameworks has introduced agent skills, modular packages containing instructions and executable code that dynamically extend agent capabilities.<n>While this architecture enables powerful customization, skills execute with implicit trust and minimal vetting, creating a significant yet uncharacterized attack surface.<n>We conduct the first large-scale empirical security analysis of this emerging ecosystem, collecting 42,447 skills from two major marketplaces.
  arXiv  Detail & Related papers  (2026-01-15T12:31:52Z)
• The Trojan in the Vocabulary: Stealthy Sabotage of LLM Composition [31.827344197678126]
  Tokenizer transplant introduces a supply-chain vulnerability.<n>By exploiting the geometry of coefficient reuse, our attack creates an asymmetric realizability gap.<n> Empirically, the attack is training-free and achieves spectral mimicry to evade outlier detection.
  arXiv  Detail & Related papers  (2025-12-31T19:00:03Z)
• Detecting Semantic Clones of Unseen Functionality [7.660632979515074]
  We re-evaluate six state-of-the-art models, including both task-specific models and generative LLMs, on the task of detecting clones of unseen functionality.<n>We propose and evaluate the use of contrastive learning to improve the performance of existing models on clones of unseen functionality.
  arXiv  Detail & Related papers  (2025-10-05T10:45:52Z)
• CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification [65.46685389276443]
  We ground our work on CLIP, a vision-language pre-trained encoder model that can perform zero-shot classification by matching an image with text prompts.<n>We then formulate purification risk as the KL divergence between the joint distributions purification process.<n>We propose two variants for our CLIPure approach: CLI-Diff which models the likelihood of images' latent vectors, and CLIPure-Cos which models the likelihood with the cosine similarity between the embeddings of an image and a photo of a.''
  arXiv  Detail & Related papers  (2025-02-25T13:09:34Z)
• Law of the Weakest Link: Cross Capabilities of Large Language Models [102.91861246827797]
  We show that Large Language Models (LLMs) exhibit the "Law of the Weakest Link," where cross-capability performance is significantly constrained by the weakest component. These results highlight the under-performance of LLMs in cross-capability tasks.
  arXiv  Detail & Related papers  (2024-09-30T05:12:01Z)
• Skill-Mix: a Flexible and Expandable Family of Evaluations for AI models [50.11814354654953]
  Key ability of an AI agent is to flexibly combine, as needed, the basic skills it has learned. This work introduces Skill-Mix, a new evaluation to measure ability to combine skills.
  arXiv  Detail & Related papers  (2023-10-26T16:55:05Z)
• GPTCloneBench: A comprehensive benchmark of semantic clones and cross-language clones using GPT-3 model and SemanticCloneBench [1.8687918300580921]
  We present a comprehensive semantic clone and cross-language clone benchmark, GPTCloneBench by exploiting SemanticCloneBench and OpenAI's GPT-3 model. From 79,928 clone pairs of GPT-3 output, we created a benchmark with 37,149 true semantic clone pairs, 19,288 false semantic pairs(Type-1/Type-2), and 20,770 cross-language clones across four languages (Java, C, C#, and Python)
  arXiv  Detail & Related papers  (2023-08-26T21:50:34Z)

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.