Paper page - ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree

Source: https://huggingface.co/papers/2606.01494

Abstract

Agent skills require layered security governance due to scanner disagreement, with findings showing varying detection rates across different scanner types and attack surfaces.

Agent skills extend AI agents with reusable instructions, tools, scripts, references, and workflows, establishing a security boundary distinct from both model safety and traditional package-malware detection.ClawHub Security Signalsis a sanitized dataset of 67,453 latest public OpenClaw skill versions. Each row pairs redacted SKILL.md content and sanitized bundled files where present with a finalClawScan registry verdictand evidence from three scanner families:VirusTotal,static heuristic analysis, andNVIDIA SkillSpector. Rather than estimating malicious-skill prevalence, we study scanner disagreement. The three scanners rarely flag the same skills: any pair overlaps on at most 10.4% of their combined positives, only 0.69% of skills are flagged by all three, and 81.9% of flagged skills are identified by a single scanner. The disagreement is structured by attack surface. SkillSpector, which raisessemantic agentic-risk advisoriesrather thanmalware-reputation signals, is positive for 19,209 of 25,504 suspicious rows (75.3%) but only 14 of 206 malicious rows (6.8%). The malicious-verdict region shows the inverse profile: 150 of 206 malicious rows (72.8%) areVirusTotal-positive, consistent with bundled-code malware evidence. These results show that agent-skill security requires layered governance, not single-scanner allow/block decisions. The corpus is released as a sanitized silver-standard dataset: labels are the registry’s automated verdicts, not human-annotated ground truth, and the release represents an early, versioned snapshot intended to support the community while a human-annotated subset is developed. Further research is encouraged, including models tailored for skill-security triage.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2606\.01494

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.01494 in a model README.md to link it from this page.

Datasets citing this paper1

#### OpenClaw/clawhub-security-signals Viewer• Updatedabout 2 hours ago • 67.5k • 84 • 24

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.01494 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.