ClawHub
Back to skill

Security audit

工具移植工具

Security checks for vulnerabilities and agentic risk

Overview

This skill has a coherent migration purpose, but it can change agent tool configurations and use real secrets without enough scoping or guardrails.

Review any bundle before importing it, back up current agent configuration, use least-privilege API keys, and only run the fill step in a trusted destination environment. Treat imported MCP commands as code that can change what your agent can run later.

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 (2)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill instructs users to run import/export operations that change local agent configuration, but it does not clearly warn that these commands can modify files and settings in the target environment. In a configuration-migration skill, that omission increases the risk of unintended changes, overwrites, or importing untrusted tool definitions into local agent directories.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The placeholder-fill workflow tells the user to read a .env file and replace placeholders, but it does not clearly warn that this action injects real secrets into the destination environment. Because this skill is specifically designed to move tool configurations across environments, the missing warning makes accidental credential exposure or unsafe propagation of secrets more likely.

Static analysis

No suspicious patterns detected.