le2le-blog-writer
Security checks across malware telemetry and agentic risk
Overview
This is a simple Chinese blog-writing skill that only gives writing-style instructions and does not request code execution, credentials, files, network access, or persistence.
This skill appears safe to install for drafting Chinese blog articles. Users should still review generated articles for factual accuracy, originality, copyright concerns when providing source material, and whether AI-use disclosure is appropriate for their publishing context.
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
66/66 vendors flagged this skill as clean.