ClawHub
Back to skill

Security audit

Awesome Design Skills

Security checks for vulnerabilities and agentic risk

Overview

This skill is a design-skill directory, but it recommends installing mutable third-party skills and unpinned packages into trusted agent locations without enough safety guardrails.

Review each linked repository and package before installing, prefer pinned commits or releases, avoid global installs where possible, and clone to a temporary review directory before copying anything into `~/.claude/skills`. This does not appear malicious, but it should be treated as a Review item because it can change future agent behavior through third-party code.

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 (2)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:23
Finding

Unpinned Remote Repositories Installed into the Agent Skill Directory

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
SKILL.md:66
Finding

Unpinned Python and Global npm Dependency Installation

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (4)

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 110)May include surrounding context.

md
## Security Notes

All skills listed here have been reviewed for safety:
- No `curl | sh` pipes or obfuscated code
- No credential harvesting (env var collection)
- No base64 decoding of hidden payloads
- No raw IP URL connections

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation description uses broad phrases like 'help me design' and 'recommend a design skill', which can match ordinary conversation and cause the skill to activate unexpectedly. In a skill that recommends tools and installation commands for third-party repositories, accidental invocation increases the chance of steering users toward unreviewed code or filesystem-modifying actions without clear intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill prominently presents many 'git clone' commands targeting ~/.claude/skills but does not warn that these commands fetch third-party code and modify the local filesystem. Because the file is framed as a curated, verified guide, users may place undue trust in the recommendations and execute them without understanding supply-chain or persistence risks.

Content

No source excerpt is available for this finding.

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 · SKILL.md (reported line 40)May include surrounding context.

md
| Skill | What It Does | Install | Source |
|-------|-------------|---------|--------|
| **SVG Logo Designer** | Professional vector logos with 3-5 concepts per project. Horizontal, vertical, square, icon-only layouts. Clean semantic SVG. | `git clone https://github.com/rknall/claude-skills ~/.claude/skills/rknall-claude-skills` | [GitHub](https://github.com/rknall/claude-skills) |
| **Algorithmic Art** | Parametric geometry, custom color theory, and interactive visualizations. Generative art with SVG. | Part of [Anthropic Skills](https://github.com/anthropics/skills) | [GitHub](https://github.com/anthropics/skills) |

### Image Generation

Static analysis

No suspicious patterns detected.