ClawHub
Back to skill

Security audit

Code Quality

Security checks for vulnerabilities and agentic risk

Overview

This skill is a lightweight code-quality guidance document; it requests command execution, but the artifact does not contain hidden scripts, persistence, exfiltration, or destructive behavior.

Install only if you are comfortable with a code-assistant skill that may use shell execution for development tasks. Review or constrain any proposed commands before running them, especially commands that modify files, deploy code, install packages, or use secrets.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
91% confidence
Finding
The skill declares the exec tool even though its stated purpose is code quality guidance, style checking, and review. This expands the skill's capability from passive analysis into command execution without a clear, scoped justification, increasing the risk of unintended or unsafe shell actions if the agent or prompt chain invokes it.

Intent-Code Divergence

Low
Confidence
78% confidence
Finding
The documentation presents the skill as producing structured review output, but later sections imply command execution may occur. This mismatch can mislead users and orchestrators about the operational behavior of the skill, reducing informed consent and making unsafe execution more likely in contexts where only analysis was expected.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The skill references command execution and operational prerequisites but does not clearly warn users that invoking it may cause shell actions or environment interaction. In a skill that includes exec, unclear disclosure increases the chance that users or higher-level agents trigger commands without understanding side effects, permissions, or data exposure risks.

Static analysis

No suspicious patterns detected.