ClawHub
Back to skill

Security audit

Mini Coder Max

Security checks for vulnerabilities and agentic risk

Overview

This is a coding-workflow skill with broad activation and optional web research, but its behavior is disclosed, purpose-aligned, and not deceptive or persistent.

Install this if you want a coding assistant that may take a structured, autonomous approach to code tasks. Be aware that it can activate broadly on coding-related prompts and may use web research for documentation, package versions, errors, and best practices.

A.I.G

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

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

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger keywords are extremely broad for a high-autonomy coding skill, making accidental activation likely during ordinary requests involving code, fixes, or architecture. In context, this is more dangerous because the skill is designed to act autonomously and can perform planning, implementation, review, and potentially research, so over-triggering can unexpectedly escalate the scope of actions taken.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill instructs the agent to use web search and fetch tools but does not clearly require explicit user awareness or consent before external network access occurs. This creates a risk of unexpected data disclosure through outbound requests, surprise behavior, or retrieval from untrusted sources, especially because the skill presents research as a normal part of execution.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.