Security audit

Acul Screen Generator

Security checks for vulnerabilities and agentic risk

Overview

The skill is purpose-aligned for Auth0 login screen generation, but its Vanilla JS templates promote unsafe HTML construction in authentication pages.

Review carefully before installing for Vanilla JS ACUL work. Prefer the React path or require the JS templates to be changed to DOM APIs/textContent with validated HTTPS icon URLs before using generated code in any real login flow, especially production.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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 (1)

T09 · Insecure Skill Coding Practices

Error

Location: assets/js-templates/login-id.js:18
Finding: DOM-Based Cross-Site Scripting Through Unescaped SDK Values
Content: View full analysis
` ${conn.iconUrl ? `` : ''} Continue with ${conn.displayName} `).join('') return `
${manager.screen.texts?.separatorText ?? 'Or'}

${buttons}
` } function renderErrors() { if (!manager.transaction.hasErrors) return '' const msgs = manager.getErrors().map(e => `
${e.message}
`).join('') return `
${msgs}
` } function render() { const container = document.getElementById('app') container.innerHTML = `

${manager.screen.texts?.title ?? 'Log in'}
${renderErrors()}
${manager.screen.texts?.usernameLabel ?? getIdenti ...[truncated 7247 chars]
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill description ends with a broad catch-all trigger: 'any task involving Auth0 Universal Login customization...' which can cause the skill to activate for loosely related requests outside its intended scope. Over-broad activation increases the chance that the agent invokes this skill in the wrong context, leading to inappropriate guidance, unsafe file changes, or disclosure of internal project context to an unnecessary workflow.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low