ClawHub
Back to skill

Security audit

Mini Coder Max

Security checks for vulnerabilities and agentic risk

Overview

This is a general coding-workflow skill with broad activation terms, but its behavior is disclosed and aligned with building and reviewing code.

Install this if you want a broad coding workflow skill that may activate for common coding verbs like code, build, fix, and refactor. Review its plan before allowing large edits, dependency changes, or network research on sensitive projects.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill declares very broad trigger keywords such as 'code', 'build', 'fix', 'create', and 'develop', which are common in ordinary requests and can cause the skill to activate in many contexts beyond a clearly bounded coding workflow. In an autonomous coding agent, ambiguous activation increases the chance of unintentional invocation, overreach, and execution of higher-capability behavior when the user did not explicitly intend to delegate a full coding workflow.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.