ClawHub
Back to skill

Security audit

LayerBack Image to VSDX

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed LayerBack diagram converter that asks before uploading user-selected images and did not show hidden or unrelated behavior.

Install only if you are comfortable sending selected diagram images to LayerBack for conversion. Confirm the file is not sensitive, keep the API key in the environment rather than chat or files, and consider pinning or verifying the installer command before global installation.

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 (3)

Rp1

Medium
Category
MCP Rug Pull
Confidence
85% confidence
Finding
The install command uses `npx -y skills@latest`, which fetches and executes the latest published package version at install time rather than a pinned, reviewed version. If the upstream package is compromised or a breaking/malicious release is published, users following the README could execute untrusted code on their system during installation.

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill instructs the agent to access environment variables, read local files, write output files, and make network requests, but it does not declare any explicit tool scope or permission boundaries. This increases the chance of overbroad agent execution, especially because the workflow involves uploading local user files to a remote service and handling an API key from the environment.

Natural-Language Policy Violations

Low
Confidence
89% confidence
Finding
The section heading and link labels at L040-L047 are presented in Chinese while the rest of the skill is in English. This imposes a locale/language assumption without opt-in or explanation, which matches the policy category for language or locale constraints.

Static analysis

No suspicious patterns detected.