ClawHub
Back to skill

Security audit

Responsive Design

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent responsive-design reference skill with no hidden runtime behavior; its main risk is unpinned installation commands.

Install only from a source you trust. Prefer a pinned ClawHub version or immutable Git commit instead of `@latest` or a GitHub `main` branch, and avoid running installation commands with elevated privileges.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (3)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:34
Finding

Unpinned ClawHub Package Is Downloaded and Executed During Installation

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
README.md:27
Finding

Mutable GitHub Source Is Passed to an Unpinned npx Installer

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
README.md:33
Finding

README Recommends Executing the Mutable Latest ClawHub Release

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • 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
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The README instructs users to execute npx add against a GitHub-hosted resource without pinning to a specific immutable version, tag, or commit. That creates a supply-chain risk: if the upstream repository changes or is compromised, future installs may fetch unexpected or malicious content.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

Using npx clawhub@latest install responsive-design explicitly requests the latest version at execution time, which is non-deterministic and increases exposure to a compromised or malicious newly-published release. This is a classic supply-chain risk because users execute remote code before reviewing it.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 46)May include surrounding context.

From your project root:

bash
mkdir -p .cursor/skills
cp -r ~/.ai-skills/skills/frontend/responsive-design .cursor/skills/responsive-design

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 62)May include surrounding context.

From your project root:

bash
mkdir -p .claude/skills
cp -r ~/.ai-skills/skills/frontend/responsive-design .claude/skills/responsive-design

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 69)May include surrounding context.

Claude Code (global)

bash
mkdir -p ~/.claude/skills
cp -r ~/.ai-skills/skills/frontend/responsive-design ~/.claude/skills/responsive-design

External Model or Provider Selection

Medium
Category
Excessive Agency
Confidence
90% confidence
Finding

Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: responsive-design
model: standard
---

# Responsive Design

Rp1

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The installation instruction uses npx clawhub@latest install responsive-design, which pulls and executes the latest published package version at runtime rather than a pinned, reviewed release. If the upstream package is compromised or a malicious version is published, users following the skill could execute attacker-controlled code on their system.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.