ClawHub

Hsk Learning

Security checks across malware telemetry and agentic risk

Overview

This appears to be a real local HSK study tool, but it needs Review because one quiz-log tool can read caller-specified local paths beyond the documented quiz-log scope.

Install only if you are comfortable with the skill scanning your OpenClaw memory markdown files for Chinese vocabulary. Avoid giving hsk_parse_quiz_log arbitrary paths, and prefer restricting it to known quiz-performance files until the package validates paths. Do not enable cron automation unless you have reviewed exactly which memory files will be scanned and where reports are written.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
88% confidence
Finding
The hsk_parse_quiz_log function accepts a caller-controlled filePath, resolves relative paths against the project root, and parses any existing file without constraining access to the intended memory/quiz-log directory. This broad file-read capability exceeds the skill's HSK-learning purpose and can expose unrelated local files if an attacker supplies sensitive paths.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The README advertises automatic scanning of conversation logs and memory files but does not disclose privacy implications, consent expectations, or scope limitations. In a learning skill, this can lead users to unknowingly process sensitive personal text, creating avoidable privacy and data-handling risk even if no exfiltration is described.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The cron-job guidance encourages recurring automated scans and reports without warning that background jobs will repeatedly access user data. This increases the chance of unnoticed ongoing processing of sensitive conversations or notes, especially if users copy setup instructions without understanding the privacy impact.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal