Security audit
Cn Smart Reply
Security checks across malware telemetry and agentic risk
Overview
This skill only generates canned Chinese reply suggestions and does not access private data, networks, or system settings.
This appears safe for generating sample replies. Review generated text before sending, especially because the skill says it is automatically generated and not human reviewed. The documentation includes promotional links, but they are not used by the runtime script.
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.
Static analysis
No suspicious patterns detected.