ClawHub
Back to skill

Security audit

ui-ux-design

Security checks for vulnerabilities and agentic risk

Overview

This UI/UX design skill is coherent and uses a disclosed external design API, but users should avoid sending sensitive product details unless they trust that service.

Install only if you are comfortable using ai-skills.open-idea.net for UI/UX design help. Treat prompts, product names, goals, and design context sent to the API as external data sharing, do not include secrets or regulated information, and confirm charges before using the paid design.plan operation.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The manifest description is written as a Chinese-only usage statement, and the document consistently presents the skill in Chinese without indicating that users may choose another language. Under the stated policy, forcing a specific language or locale without user opt-in is a natural-language policy violation.

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The entire skill guidance is written as prescriptive behavior rules in Chinese, and there is no indication that the user can opt into another language or that the skill is intentionally limited to a Chinese-speaking context. Under the stated policy, forcing a specific language without user choice is a natural-language locale-policy violation.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The documentation instructs users to send authenticated requests to a remote third-party service but does not warn that prompt contents, product details, or other user-supplied data will leave the local environment. In an agent skill context, this omission is security-relevant because operators may unknowingly transmit sensitive design requirements, internal project names, or proprietary product information off-system.

External Transmission

Medium
Category
Data Exfiltration
Content
```sh
BASE="${AI_SKILLS_API_URL:-https://ai-skills.open-idea.net/api/v1}"
curl -sS -X POST "$BASE/ui-ux-design/design.plan" \
  -H "Authorization: Bearer $UI_UX_DESIGN_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: 生成一个新的UUID" \
Confidence
94% confidence
Finding
The example performs an authenticated POST to an external endpoint using a bearer token and includes user-provided content in the JSON body. In a skill repository, this creates a real external-transmission path that could expose sensitive business context or user data if consumers follow the example without understanding the trust boundary.

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The entire guide is written only in Chinese, and there is no indication that the skill offers a language choice or that it is explicitly limited to a Chinese-speaking or region-specific audience. Per the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Static analysis

No suspicious patterns detected.