Back to skill

Security audit

presales-tech-support

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only Chinese presales diagnostic helper that does not install code, request credentials, or persist access.

Install only if a Chinese-language diagnostic brief is acceptable for your workflow. Avoid pasting secrets, customer credentials, private tokens, or unnecessary personal data into diagnostic prompts, and verify any recommended commands or claims about vendor errata and GitHub issues before acting on them.

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
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The skill hard-requires Chinese output style and does not offer any user language choice or justify a locale restriction. This is dangerous because it can exclude users, cause misunderstanding of technical guidance, and reduce the operator's ability to safely validate or act on diagnostics if they are not fluent in Chinese.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.