ClawHub
Back to skill

Security audit

Acpx Coding Default

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent shortcut for using the acpx CLI for coding tasks, with no bundled code, persistence, credential handling, or hidden behavior found.

Install this only if you want coding requests routed through the local acpx CLI. Treat it like any coding-agent execution path: review commands and prompts for sensitive repositories, and expect it may edit files or run project tooling when asked to do coding work.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly instructs agents to invoke a shell-executed external CLI for coding tasks, but provides no safety guidance about command execution side effects, prompt/argument injection risks, or trust boundaries around the repo and prompt contents. In an agent setting, normalizing direct exec as the default path increases the chance that untrusted task data or repository content will be passed into shell commands or a powerful coding tool without adequate review.

Static analysis

No suspicious patterns detected.