ClawHub
Back to skill

Security audit

TypeScript

Security checks across malware telemetry and agentic risk

Overview

This TypeScript skill is a documentation-style helper with disclosed, scoped local preference memory and no evidence of hidden or destructive behavior.

Before installing, understand that the skill may read and maintain TypeScript-specific preferences and memory in ~/Clawic/data/typescript/. Review or delete those files if you do not want prior context reused across sessions.

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)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs the agent to read from and write to persistent user-specific files under `~/Clawic/data/typescript/` without any user-facing disclosure or consent step. Even though the purpose appears to be convenience and preference persistence, this creates a privacy and data-governance risk because the agent may access prior context and store new user information silently across sessions.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.