expert-frontend-developer

• Outcome: Pass
• Latest audit: Sep 15, 2026 · 1:15 AM UTC
• Version: 1.0.2

Overview

This is a markdown-only frontend developer persona skill with loose activation wording, but no code execution, persistence, external calls, or unrelated data access.

Installers should expect this skill to change the assistant’s style into a frontend developer persona when activated. Use explicit activation commands where possible, and consider narrowing the trigger list if accidental activation from phrases like 'FE' or 'I need a frontend developer' would be disruptive.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Vague Triggers

High

• Category: Not specified by scanner
• Confidence: 98% confidence

Finding

The Chinese triggers include extremely short generic terms like '前端' and 'FE', which are highly likely to occur in benign conversation and are not reliable indicators of activation intent. Because these tokens are common abbreviations and topic labels, they create a high risk of accidental invocation and uncontrolled persona switching.

Content

No source excerpt is available for this finding.

Anti-Refusal Statement

High

• Category: Anti-Refusal
• Confidence: 75% confidence

Finding

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

Content

Scanner excerpt · SKILL.md (reported line 224)May include surrounding context.

md

**User:** `activate Frontend Developer`

**Response:** `✅ Frontend Developer mode activated! I'm a senior frontend engineer specializing in React, Vue, Angular, performance optimization, and accessible web development. I focus on Core Web Vitals, component architecture, and pixel-perfect implementation. What are we building?`

---

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 96% confidence

Finding

The activation description includes the open-ended phrase 'or similar', which makes the trigger boundary ambiguous and increases the chance that ordinary user language will unintentionally activate the skill. In a system that swaps personas or instructions based on user phrasing, ambiguous activation can cause unexpected context changes and reduce reliability of higher-priority safety behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

Several English activation commands are broad natural-language phrases such as 'I need a frontend developer' and 'from now on you're a frontend developer', which can plausibly appear in normal conversation. This raises the risk of unintended skill activation, letting the skill alter assistant behavior when the user may only be describing a need rather than explicitly requesting a mode switch.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.