Back to skill

Security audit

Wrangler HTML Publish

Security checks for vulnerabilities and agentic risk

Overview

ClawScan’s verdict is benign with medium confidence: the scanners found no clear harmful behavior, though parts of the skill were only partially inspected.

The verdict is benign, but confidence is medium and coverage is incomplete: two JavaScript files were only partially interpreted, and tool-misuse analysis was degraded. Consider that uncertainty before installing, especially if you need assurance about those files or runtime permissions.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

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 22)May include surrounding context.

md
- `scripts/files.mjs`:Node.js 内置模块实现,无需安装依赖;提供默认路径、单 HTML 归档、按白名单构建 staging。它不联网、不部署、不做内容隐私判定。

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 25)May include surrounding context.

md
- `tests/files.test.mjs`:离线文件与路径测试。

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · tests/files.test.mjs (reported line 59)May include surrounding context.

js
test('拒绝路径穿越、隐藏文件、后端配置和重复目标', t => {
  const root = sandbox(t);
  fs.writeFileSync(path.join(root, 'page.html'), 'synthetic');
  for (const target of ['../escape.html', '/absolute.html', 'a\\b.html', 'C:/page.html', '.env', 'functions/test.html', '_worker.js', 'wrangler.json', '_headers']) {
    assert.throws(() => stage(plan(root, [['page.html', target]]), path.join(root, 'stage')));
  }
  assert.throws(() => stage(plan(root, [['page.html', 'a.html'], ['page.html', 'A.html']]), path.join(root, 'stage')), /重复/);

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.