ClawHub
Back to skill

Security audit

SciDraw AI Scientific Illustration

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent SciDraw AI image-generation helper that discloses its API key use, network calls, credit use, and local output file writes.

Before installing, understand that this skill sends prompts to SciDraw AI and uses account credits when generation is confirmed. Store the API key only in your local environment, keep the default SciDraw API endpoint unless you intentionally trust another endpoint, and choose output paths where overwriting a generated image would not matter.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill instructs the agent to use environment variables, read and write local files, and make network requests, but it does not declare any corresponding tool scope or permissions. This creates an undeclared capability boundary where a host may grant broader access than users expect, increasing the risk of unintended file access, secret exposure, or outbound requests without clear authorization.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
key creation link above.
- Do not silently substitute another image provider. Use a different backend
  only when the user explicitly requests it.
- Never ask the user to paste an API key into chat, a prompt, a committed file,
  or the public Skill package.

## Configure the SciDraw AI API
Confidence
80% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Natural-Language Policy Violations

Low
Confidence
82% confidence
Finding
The section heading and resource links are presented only in Chinese, while the rest of the skill is primarily in English. This imposes a locale/language choice in part of the skill content without explicit user opt-in or an offered language alternative.

Static analysis

No suspicious patterns detected.