Double Check Article
Security checks across malware telemetry and agentic risk
Overview
This skill is a simple Chinese article proofreading helper with no evidence of hidden access, code execution, or data exfiltration.
Safe to install as a proofreading aid. Only provide drafts you are comfortable letting your agent process, but this skill does not show hidden data access, persistence, or external transmission behavior.
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.