Agent Code Debugger

• Outcome: Review
• Latest audit: Sep 15, 2026 · 1:33 AM UTC
• Version: 1.0.0

Overview

This skill is a local code-analysis helper that inspects provided code strings and returns debugging advice without accessing files, networks, credentials, or persistent system state.

This appears suitable to install as a debugging helper. Treat its quick-fix output as suggested code, review changes before applying them to a real project, and be aware that its issue detection is simple regex-based guidance rather than a full compiler, linter, or security audit.

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

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (5)

Undeclared Tool Scope

Medium

• Category: MCP Least Privilege
• Confidence: 84% confidence

Finding

The skill documentation demonstrates code-related capabilities using require(...) and debugger-style operations, but the manifest does not declare any tool scope such as permissions or allowed-tools. This creates ambiguity about what execution capabilities the skill expects, which can lead to over-broad runtime access or unsafe invocation patterns if a host grants default shell/code execution privileges.

Content

No source excerpt is available for this finding.

Unrestricted Tool Access

Medium

• Category: Excessive Agency
• Confidence: 80% 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 · index.js (reported line 222)May include surrounding context.

js

pattern: /eval\s*\(/g,
    languages: ['javascript', 'typescript'],
    name: 'eval_usage',
    description: 'eval() is dangerous and can execute arbitrary code',
    severity: 'critical',
    fix: 'Avoid eval(), use safer alternatives like JSON.parse() or Function constructor'
  },

Unrestricted Tool Access

Medium

• Category: Excessive Agency
• Confidence: 80% 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 · index.js (reported line 238)May include surrounding context.

js

pattern: /eval\s*\(/g,
    languages: ['javascript', 'typescript'],
    name: 'eval_usage',
    description: 'eval() is dangerous and can execute arbitrary code',
    severity: 'critical',
    fix: 'Avoid eval(), use safer alternatives like JSON.parse() or Function constructor'
  },

Description-Behavior Mismatch

Medium

• Category: Not specified by scanner
• Confidence: 91% confidence

Finding

The manifest description presents the skill as an analyzer/advisor for debugging assistance, issue identification, and fix suggestions. The quickFix function goes beyond suggestion by programmatically rewriting supplied code, which is a materially different behavior than analysis-only assistance.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low

• Category: Not specified by scanner
• Confidence: 86% confidence

Finding

The manifest describes a code debugger focused on issue detection, debugging guidance, and fix suggestions across languages. The detectAIPatterns function instead classifies code as potentially AI-generated based on comment density and stylistic markers, which is not an obvious implementation detail of debugging assistance.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.dynamic_code_execution

Dynamic code execution detected.

Critical

• Code: suspicious.dynamic_code_execution
• Location: index.js:222