ClawHub
Back to skill

Security audit

Telegram Wim Wsl File Delivery

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to use local shell and file operations, but the supplied evidence does not show hidden behavior, exfiltration, destructive actions, or persistence.

Install only if you are comfortable letting the skill guide an agent through local shell commands and file operations. Review commands before execution, avoid running it in directories with secrets unless necessary, and prefer a sandbox or limited workspace for first use.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill instructs the agent to use shell execution extensively (`exec` with `ls`, `file`, `cp`, `chmod`, `mkdir`, `grep`, and `node`) but does not declare a corresponding shell/code-execution permission boundary. This creates a capability mismatch: a caller or reviewer may believe the skill is low-risk while it can actually perform host-local command execution and file access, increasing the chance of unintended data exposure or command abuse if file paths or targets are influenced by untrusted input.

Static analysis

No suspicious patterns detected.