ClawHub
Back to skill

Security audit

设计分析直觉高效贴合心智模型的用户体验

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a UX guidance document, but it requests broad command and file-writing authority without explaining or limiting that power.

Install only if you are comfortable with the skill being able to read files, run shell commands, and write files. Before using it, keep command execution and file edits under explicit user direction, and avoid granting it broad access to private repositories or sensitive local data unless the task truly requires it.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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)

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill is presented as a UX/design analysis tool, but its declared toolset includes generic exec and write capabilities without narrowly scoping when or why those powerful actions are needed. This creates capability creep: an agent or user may invoke filesystem or shell actions that exceed the reasonable expectations of a UX analysis skill, increasing the chance of unsafe command execution or unintended system changes.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documentation advertises exec/write capabilities and references command execution, yet it does not give a prominent warning that the skill may run commands or modify local files. In an agent context, this weakens user awareness and consent, making it easier for the skill to be used in ways that alter the host environment unexpectedly.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.