ClawHub
Back to skill

Security audit

Run

Security checks for vulnerabilities and agentic risk

Overview

This skill openly describes broad code execution, automation, and production deployment powers, but its triggers and safeguards are too loosely scoped for automatic trust.

Review carefully before installing. This skill should only be used in a tightly controlled environment where code execution, dependency installation, scheduled jobs, persistence, network access, and production deployment all require explicit user approval and clear scope.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (4)

Vague Triggers

High
Confidence
96% confidence
Finding
The trigger phrase "Run this script" is broad and maps directly to arbitrary code execution, making accidental or overly permissive invocation likely. In an agent setting, common user phrasing can unintentionally activate execution behavior, increasing the chance of unsafe code runs without sufficient confirmation or scoping.

Vague Triggers

High
Confidence
97% confidence
Finding
The production deployment trigger "Run this in production" is dangerously ambiguous for a capability that can deploy logic to cloud-edge nodes. A casual natural-language request could cause live deployment actions in sensitive environments, leading to service disruption, unauthorized changes, or propagation of malicious code.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill description emphasizes secure sandboxing and broad execution power but does not clearly warn users that it enables arbitrary code execution, automation, and deployment with potentially significant side effects. This can mislead users or downstream agents into underestimating the risk and invoking the skill in contexts where stronger caution is necessary.

Unrestricted Tool Access

Medium
Category
Excessive Agency
Content
## Core Primitives
```FUNCTIONS = {
  "execute": {
    "scope":   "Run arbitrary code snippets with auto-dependency injection",
    "trigger": "Run this script"
  },
  "automate": {
Confidence
92% confidence
Finding
The primitive explicitly supports running arbitrary code snippets with auto-dependency injection, which is inherently high risk if not tightly governed by policy and trust controls. Although the skill claims sandboxing and some safeguards, the combination of unrestricted execution and dependency resolution expands the attack surface for malicious payloads, sensitive operations, or supply-chain abuse.

Static analysis

No suspicious patterns detected.