ClawHub
Back to skill

Security audit

Tattoo Design Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward tattoo image generator that sends user-provided prompts and a Neta token to the disclosed image API.

Install only if you are comfortable sending tattoo prompts, optional reference UUIDs, and your Neta API token to the external Neta/TalesOfAI service. Prefer passing the token from an environment variable rather than typing it directly into shell history, and avoid sensitive client or personal reference material unless you trust the provider’s handling of that data.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill declares only Bash but omits any explicit permission/scoping for network access, even though its stated purpose requires sending prompts and tokens to an external API. This creates a transparency and governance gap: users and platforms may not realize the skill can exfiltrate user prompts, reference IDs, and API tokens over the network.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding
The documented behavior says the skill uses Neta AI for tattoo generation, but the analyzed behavior indicates it actually calls a different third-party service and supports broader image generation features than advertised. That mismatch is dangerous because users may disclose prompts, tokens, or reference assets under false assumptions about where data goes and what the tool can do, undermining consent, data handling expectations, and policy enforcement.

Static analysis

No suspicious patterns detected.