ClawHub
Back to skill

Security audit

vx-project

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only vx project management skill whose setup, tool installation, and configuration examples are disclosed and aligned with its purpose.

Install this if you want vx-specific project setup guidance. Be aware that following the guide may install development tools, create or update vx.toml and vx.lock, configure project hooks, and optionally write vx AI skill metadata under ~/.vx, so review generated configuration before committing or running hooks in sensitive repositories.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 8)May include surrounding context.

md
# VX Project Management Guide

> **Quick start**: Run `vx init` to create `vx.toml`, `vx setup` to install all tools, `vx dev` to enter the dev environment. For existing projects, just run `vx setup` after cloning.

## Project Setup

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 276)May include surrounding context.

md
- A numeric `vx.toml` pin that disagrees with the effective toolchain is warned about
  on stderr and makes `vx check` exit non-zero. The toolchain file still wins; the
  warning exists so a dead pin cannot go unnoticed.
- For a repository that already pins with rustup, write `rust = "rustup-managed"`
  instead of omitting `rust` with an explanatory comment.
- An explicit `vx cargo@1.90.0` always goes through vx.

Unsafe Defaults

Medium
Category
Tool Misuse
Confidence
60% confidence
Finding

Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 334)May include surrounding context.

toml
[env]
NODE_ENV = "development"
DATABASE_URL = "postgresql://localhost:5432/dev"
API_KEY = { env = "API_KEY", required = true }

Static analysis

No suspicious patterns detected.