{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.07131", "kind": "paper", "url": "https://arxiv.org/abs/2606.07131"}], "authors": ["Wenbo Guo", "Wei Zeng", "Chengwei Liu", "Xiaojun Jia", "Yijia Xu", "Lei Tang", "Yong Fang", "Yang Liu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.07131", "source_url": "https://arxiv.org/abs/2606.07131"}, "categories": ["Agents", "Language & Knowledge", "Logistics & Operations"], "description": {"en": "MalSkillBench is a runtime-verified benchmark of malicious agent skills, with 3,944 malicious skills labeled along a taxonomy, measuring detection tool effectiveness."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.07131", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.07131", "title": "MalSkillBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Nanyang Technological University", "Sichuan University", "Nankai University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.07131", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.07131", "source_url": "https://openalex.org/W7163907095"}, "key": "claire-radar:2606.07131", "modality": null, "name": "MalSkillBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_malskillbench_80086691", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "ca664a9a36048c3afdfbda71810880e58d0c7cf9fbb7825551e9700f8cc2305f", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.07131"}, "publisher": null, "released": "2026-06-05", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.07131", "source_url": "https://arxiv.org/abs/2606.07131"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-07131", "source": "claire_radar", "source_benchmark_id": "2606.07131", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Logistics & Operations"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 1, "hfPaperUrl": "https://huggingface.co/papers/2606.07131", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-25", "state": "stale"}}, "status": "stale"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "349e093176a4625ee481c4416df6e4cdc46986bb6731ea513196b84549699a6b", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MalSkillBench is a runtime-verified benchmark of malicious agent skills, with 3,944 malicious skills labeled along a taxonomy, measuring detection tool effectiveness.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We present MalSkillBench, the first runtime-verified benchmark of malicious agent skills: 3,944 malicious skills labeled along a three-dimensional taxonomy of 108 cells."}, "familyId": "bmf_f88e2b4dd1af", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_malskillbench_80086691", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Logistics"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.07131", "paper": "https://arxiv.org/abs/2606.07131", "pdf": "https://arxiv.org/pdf/2606.07131", "project": null, "report": "https://arxiv.org/abs/2606.07131"}, "metrics": [], "motivation": "AI coding agents such as Claude Code and Gemini CLI increasingly extend themselves with third-party skills: markdown packages bundling natural-language instructions, executable scripts, and tool permissions.", "name": "MalSkillBench", "oneLine": "MalSkillBench is a runtime-verified benchmark of malicious agent skills, with 3,944 malicious skills labeled along a taxonomy, measuring detection tool effectiveness.", "paperTitle": "MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills", "primaryDomain": "Logistics & Operations", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.07131", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-05", "source": {"authors": ["Wenbo Guo", "Wei Zeng", "Chengwei Liu", "Xiaojun Jia", "Yijia Xu", "Lei Tang", "Yong Fang", "Yang Liu"], "categories": ["cs.CR", "cs.SE"], "id": "2606.07131", "title": "MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills", "type": "arxiv", "url": "https://arxiv.org/abs/2606.07131"}, "sourceUpdatedAt": "2026-06-19T05:32:49Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Evaluates detection tools for hybrid code-prompt skills, potentially informing supply chain security, but lacks public artifacts for reuse."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
