ClawHub
Back to skill

Security audit

Svelte

Security checks across malware telemetry and agentic risk

Overview

This Svelte skill is a documentation and coding-guidance skill with disclosed, locally scoped preference memory; users should be aware it can retain project preferences across sessions.

Before installing, understand that this skill may read and update local Svelte preference files under ~/Clawic/data/svelte/. Review or delete those files if you do not want project conventions, recurring issues, or guidance preferences retained between 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 (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly instructs the agent to read and write user-scoped files under ~/Clawic/data/svelte without any user-facing notice or consent step. That creates a privacy and boundary issue because project work can silently pull in prior context and persist new preferences, potentially exposing or retaining sensitive information across sessions.

Ssd 3

Medium
Confidence
96% confidence
Finding
The skill directs the agent to persist natural-language user preferences, habits, project shape, and recurring pain points into local memory files. Even if intended for convenience, this creates a data retention risk because freeform notes can accumulate sensitive personal, organizational, or security-relevant context that may later be reused outside the user's expectations.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.