ClawHub
Back to skill

Security audit

免费版

Security checks for vulnerabilities and agentic risk

Overview

This skill is not clearly malicious, but it asks for broad command and file access for a very general AI/API automation purpose.

Review this before installing. It may be appropriate only if you intentionally want a broad automation skill that can use external AI APIs and local file/command tools. Avoid using it with secrets or private data unless the calling agent enforces explicit confirmation and tight command/file boundaries.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill advertises itself for very broad use cases such as general AI calls, intelligent dialogue, agent orchestration, and workflow automation. In combination with declared powerful tools like read, write, and exec, overly broad matching can cause the agent to invoke this skill for routine prompts and unnecessarily grant command execution, file modification, or external API access in contexts where users did not expect it.

Missing User Warnings

High
Confidence
95% confidence
Finding
The skill exposes read, exec, and write capabilities and is described as integrating third-party APIs, yet it does not prominently warn users that invoking it may run shell commands, modify files, or send data to external services. In an agent ecosystem, this missing disclosure is dangerous because users may provide sensitive inputs under the assumption of a normal chat or model call, leading to unintended data exfiltration, filesystem changes, or execution of risky operations.

Static analysis

No suspicious patterns detected.