ClawHub
Back to skill

Security audit

art-evaluation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward art-evaluation helper with disclosed, user-directed image analysis and optional image-generation behavior.

Before installing, be aware that a future complete implementation may send artwork to a local model or external image-generation service; use it only with images you are comfortable processing that way and review any added API or model-invocation code if the placeholders are replaced.

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
78% confidence
Finding
The skill documentation indicates script execution and model invocation capabilities, including local model deployment and generating output files, but it declares no permissions. This creates a transparency and policy-enforcement gap: a host system or reviewer may underestimate what the skill can execute, especially if underlying scripts invoke shell commands or external services.

Static analysis

No suspicious patterns detected.