ClawHub
Back to skill

Security audit

Ui Page Replication V1

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent UI replication helper; it asks the agent to inspect a user-specified page and generate matching frontend code, with no hidden install, exfiltration, persistence, or privilege escalation behavior found.

Install this only if you want Codex to inspect and recreate UI pages. Because it may capture screenshots, DOM snapshots, and network clues from the browser page, avoid using it on pages containing secrets, private customer data, or sessions you do not intend to include in local project artifacts.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The declared description presents a comprehensive UI replication and restoration skill, but the supplied code chunk contains only placeholder utility functions with no substantive functionality. The primary purpose in code is not an implemented replication workflow; it is merely a skeletal helper object. This is a material description-behavior mismatch because the described core capabilities are absent rather than just partially implemented.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
78% confidence
Finding

The invocation description includes a fixed set of Chinese phrases such as '复刻页面' and '页面还原' as trigger examples, but does not state that language selection is optional or user-driven. This can create a language/locale preference embedded in the skill definition without explicit opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description and example invocation are entirely in Chinese, including the usage phrase "复刻页面：房源管理系统", with no indication that other languages are supported or that Chinese is required for a region-specific purpose. This creates a natural-language policy concern because it implicitly constrains users to a specific language without opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list and accompanying comment are entirely in Chinese, which implies the skill activates only for Chinese-language inputs. This creates a language/locale restriction without any user opt-in or documented justification that the skill is intentionally region- or language-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language instruction states the assistant role entirely in Chinese and frames the skill behavior in that language, which imposes a language/locale expectation without any visible opt-in or alternative. This matches the policy category for language or locale constraints that are not user-selectable or explicitly justified.

Content

No source excerpt is available for this finding.