ClawHub
Back to skill

Security audit

Children Book Illustration Generator

Security checks for vulnerabilities and agentic risk

Overview

This looks like a normal image-generation helper that uses a third-party API, with privacy and token-handling disclosures that should be clearer.

Before installing, confirm you are comfortable sending story prompts and the provided API token to the third-party image service. Avoid putting private, regulated, or unpublished sensitive story material in prompts unless you trust that provider, and prefer environment variables or a secret store for the token rather than exposing it casually on the command line.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill declares only the Bash tool and documents use of an external API token and a script that likely performs network calls, but it does not explicitly declare or scope that network capability. Hidden or undeclared network access reduces transparency for reviewers and users, and can enable unexpected outbound requests involving prompts or tokens. In a skill that handles API credentials, this mismatch is more concerning because users may expose secrets to destinations they did not clearly authorize.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The script sends both the user-supplied prompt and the API token to a third-party service, but it does not clearly warn users that their input and credential will be transmitted off-box. In this skill's context, external transmission is expected for an image-generation API, but the lack of explicit disclosure still creates a privacy and credential-handling risk, especially if users assume prompts are processed locally or may include sensitive story content.

Static analysis

No suspicious patterns detected.