Back to skill

Security audit

chrome-extension-wxt

Security checks for vulnerabilities and agentic risk

Overview

ClawScan’s verdict is benign with medium confidence: the reported findings are mainly unpinned setup commands, while no malicious behavior was reported, though one referenced document was only partly inspected.

The verdict is benign, not a guarantee of safety, and confidence is medium. Before installing, consider that some setup commands fetch unpinned packages and that one referenced document was not fully inspected; use care when running setup instructions.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (14)

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 93)May include surrounding context.

md
5. For runtime behaviour, a Playwright test against `.output/chrome-mv3` (see `references/testing-publishing.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 469)May include surrounding context.

md
- `references/testing-publishing.md` - Vitest with `WxtVitest` and `fakeBrowser`, Playwright, zips, `wxt submit`, store requirements. Read when adding tests or

MCP server referenced without pinned version: 'npx wxt'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx wxt'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx wxt'.

Medium
Category
MCP Rug Pull
Confidence
82% confidence
Finding

The quick-start command explicitly executes wxt@latest, so its executable dependency can change without review even though the skill targets a specific tested version. This is a supply-chain hardening weakness rather than an MCP issue: a compromised upstream release could execute with the developer or agent's filesystem and environment access.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx wxt'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx wxt'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx vitest'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

Scanner excerpt · SKILL.md (reported line 405)May include surrounding context.

md
manifest: ({ browser, mode }) => ({
    name: mode === 'development' ? 'My Extension (dev)' : 'My Extension',
    permissions: ['storage'],
    host_permissions: ['*://*.example.com/*'],
    ...(browser === 'firefox' && {
      browser_specific_settings: {
        gecko: {

MCP server referenced without pinned version: 'npx wxt'.

Medium
Category
MCP Rug Pull
Confidence
82% confidence
Finding

The new-project instruction executes a mutable wxt@latest release despite identifying a specific version as tested. This creates an avoidable supply-chain exposure if a later release is compromised; the relevant risk is executable package resolution, not an MCP server.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx shadcn'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx shadcn'.

Medium
Category
MCP Rug Pull
Confidence
84% confidence
Finding

This actionable command executes shadcn@latest and allows that mutable CLI to modify the project. Although legitimate for UI development and unrelated to MCP, it exposes the agent's workspace and process environment to an unreviewed future release if the upstream distribution is compromised.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx playwright'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Excessive Permissions

Low
Category
Privilege Escalation
Confidence
80% confidence
Finding

Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.

Content

Scanner excerpt · SKILL.md (reported line 405)May include surrounding context.

md
manifest: ({ browser, mode }) => ({
    name: mode === 'development' ? 'My Extension (dev)' : 'My Extension',
    permissions: ['storage'],
    host_permissions: ['*://*.example.com/*'],
    ...(browser === 'firefox' && {
      browser_specific_settings: {
        gecko: {