ClawHub
Back to skill

Security audit

Wurd

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only Wurd skill with optional LLM features that are purpose-aligned, but users should treat LLM document processing and local caching as privacy-sensitive.

Safe to install as a Wurd usage guide. Before using LLM-powered plugins, assume relevant prompt or document content may be sent to the configured LLM provider and cached under .cache/llm/; use --no-cache or clear the cache when needed, avoid sensitive/proprietary documents unless that provider is approved, and only load external plugins from trusted directories.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 users to configure an external LLM API and notes that LLM-powered plugins process document content, but it does not warn that prompts or source document text may be transmitted to a third-party service and cached locally. This creates a real privacy and data-handling risk, especially if users compile sensitive or proprietary markdown through the graph or table plugins without realizing content leaves the local environment.

VirusTotal

46/46 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.prompt_injection_instructions

Prompt-injection style instruction pattern detected.

Warn
Code
suspicious.prompt_injection_instructions
Location
SKILL.md:152