Back to skill

Security audit

web-design-engineer

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because it may allow unverified third-party scripts, and one referenced file was only partly inspected.

Consider the suspicious verdict before installing. The scan identifies a conditional risk from third-party scripts and incomplete inspection of one referenced file; it does not establish malicious intent. If you proceed, review the dependency guidance and avoid using the skill for pages that handle sensitive data unless the external code is verified and disclosed.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

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

md
---
name: web-design-engineer
description: |
  Build high-quality visual Web artifacts using HTML/CSS/JavaScript/React — web pages, landing pages, dashboards, interactive prototypes, HTML slide decks, animated demos, UI mockups, data visualizations, and more.
  Use this skill whenever the user's request involves a visual, interactive, or front-end deliverable, including:
  - Creating web pages, landing pages, dashboards, marketing pages
  - Building interactive prototypes or UI mockups (with device frames)
  - Building HTML slide decks / presentations
  - Creating CSS/JS animations or timeline-driven animated demos
  - T

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 194)May include surrounding context.

md
sign canvas, data visualization) available in [references/advanced-patterns.md](references/advanced-patterns.md)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 407)May include surrounding context.

md
- [references/advanced-patterns.md](references/advanced-patterns.md) — Full code template library (slide engine, device frames, Tweaks panel, animation timeline

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 355)May include surrounding context.

```

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 362)May include surrounding context.

Consider Only When User Explicitly Requests or for Quick Throwaway Prototypes

html
<!-- Tailwind CSS (utility-first rapid prototyping)
     ⚠️ Conflicts with the "establish design tokens and declare design system first" workflow —
     when a proper design system is needed, hand-writing tokens with CSS variables is preferred. -->
<script src="https://cdn.tailwindcss.com"></script>

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 381)May include surrounding context.

md
Complete the following before considering the work delivered (all items must pass):

- [ ] Browser console shows **no errors, no warnings**
- [ ] Renders correctly on **target devices/viewports** (responsive web → mobile / tablet / desktop; mobile prototype → target device; slide decks/video with fixed dimensions → scaling container adapts without distortion)
- [ ] **Interactive components** (buttons, links, inputs, cards, etc.) include states as appropriate: hover / focus / active / disabled / loading; empty/error states added where the scenario warrants them
- [ ] No text overflow or truncation; `text-wrap: pretty` applied

The skill instructs agents to load third-party CDN scripts without warning users about external requests or third-party code execution.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

CDN dependencies are normal for frontend prototypes, and the pinned versions and integrity attributes reduce risk. However, the skill explicitly permits removing integrity checks when a CDN is restricted and elsewhere supplies unpinned script URLs without integrity protection; compromised upstream code could then execute with the generated page's privileges and access its rendered data. This is a conditional supply-chain risk, not evidence of deliberate exfiltration, and the absence of a user warning alone would not establish a vulnerability.

Content

No source excerpt is available for this finding.