ClawHub
Back to skill

Security audit

Nima Skill Creator

Security checks across malware telemetry and agentic risk

Overview

This skill coherently helps create and package local Codex skills, with visible usability caveats but no evidence of hidden data transfer, credential access, or destructive behavior.

Install this if you want help creating Codex/OpenClaw skills. Before using it, confirm the target directory, review generated skills before enabling them, inspect packaged archives for unintended files, and tell the agent your preferred language if you do not want Chinese discovery prompts.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (4)

Natural-Language Policy Violations

Medium
Confidence
81% confidence
Finding
The instruction to always ask in Chinese during requirement exploration overrides user language preference and can degrade informed consent, clarity, and operator awareness. In a security-sensitive workflow, forced language switching can cause misunderstandings about generated files, commands, or scope, increasing the chance of unsafe approval or incorrect execution rather than directly enabling code execution.

Vague Triggers

Medium
Confidence
83% confidence
Finding
Telling authors to 'explain when to use the skill' without structured constraints encourages natural-language descriptions that may match common everyday requests. This increases the chance of false-positive activation, though the impact here is moderated because this is only a template and does not itself perform privileged actions.

Vague Triggers

Low
Confidence
83% confidence
Finding
Telling authors to 'explain when to use the skill' without structured constraints encourages natural-language descriptions that may match common everyday requests. This increases the chance of false-positive activation, though the impact here is moderated because this is only a template and does not itself perform privileged actions.

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The file hard-codes Chinese for requirement discovery interactions and does not provide any user language choice, fallback, or opt-in. In a skill-creation workflow, this can cause incorrect requirement capture, user exclusion, or unsafe misunderstandings if users proceed despite not fully understanding the prompts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.