ClawHub 技能开发模板
Security checks across malware telemetry and agentic risk
Overview
This is a low-risk Chinese template skill for creating ClawHub skills, with no executable code or hidden behavior found.
Safe to install as a template aid. Before publishing any generated skill, review the generated SKILL.md and package.json, replace placeholders carefully, and do not include real API keys, credentials, or private metadata.
SkillSpector
By NVIDIA
Vulnerability Patterns
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
65/65 vendors flagged this skill as clean.