ClawHub
Back to skill

Security audit

Codemod

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Codemod CLI helper for code migrations and refactors, with expected command and file-changing behavior but no evidence of hidden or deceptive actions.

Install this if you want the agent to use Codemod CLI for migrations or large refactors. Expect registry/docs lookups and Codemod CLI execution, and review dry-run results before allowing broad code changes or publishing a codemod.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The command activates on any text passed with `/codemod` and immediately treats it as a codemod task, without requiring additional confirmation, scope checks, or exclusions for unrelated/sensitive requests. In this skill, that broad trigger is more dangerous because downstream instructions direct the agent to run CLI commands and potentially initialize or modify repositories, so a loosely scoped activation can cause unintended codebase changes or tool execution from ambiguous input.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.