ClawHub
Back to skill

Security audit

代码委派基础版

Security checks across malware telemetry and agentic risk

Overview

This is a broad but disclosed coding-assistant skill with read and command-execution capability, and no hidden installer, persistence, or artifact-backed exfiltration behavior.

Install only if you are comfortable with a coding helper that can read project files and run local commands. Review commands before they run, avoid giving it secrets, and use it in a project or sandbox where code-generation and test commands are expected.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
91% confidence
Finding
The skill is presented as a focused code-delegation utility, but the later section broadens its capabilities to generic file handling, external API use, and system command execution. That scope expansion increases the chance that a user or downstream agent will authorize actions beyond the expected trust boundary, especially because the skill already has exec enabled.

Context-Inappropriate Capability

Medium
Confidence
85% confidence
Finding
Documenting external API integration in a 'basic code delegation' skill creates an unjustified channel for data egress and unexpected network access. In this context, API calls are more dangerous because users may supply proprietary code or secrets while assuming the skill only performs local code-generation assistance.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill advertises file handling, API integration, and command execution without clearly warning that these actions can modify the local environment or transmit data externally. Because the skill is allowed to use exec, unclear disclosure materially raises the risk of unintended destructive commands, data exposure, or policy violations when invoked by users or agents expecting a safer, narrower tool.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.