ClawHub
Back to skill

Security audit

Skill Review

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a review/reporting helper with no artifact-backed evidence of hidden access, persistence, destructive behavior, or data exfiltration.

Install only if Chinese-language review output is acceptable for your workflow. If you need multilingual or user-preference-aware reports, adjust the skill instructions before use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The frontmatter forces output to Chinese ('审查结论、优化建议、建议新增的 scripts/references、是否通过') regardless of user preference. This is not a direct security exploit, but it can cause misunderstandings, reduce operator visibility, and increase the chance that a user approves modifications without fully understanding the review results.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.