blog-polish-zhcn
Security checks across malware telemetry and agentic risk
Overview
The skill matches its stated blog-polishing purpose, but its output filename is partly controlled by model output and is not safely constrained to the chosen output folder.
Review before installing. Use only with non-sensitive drafts, keep outputDir inside a safe workspace, and check the returned outputPath. A safer version should restrict titleSlug to simple filename characters and verify the final path remains inside outputDir before writing.
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
64/64 vendors flagged this skill as clean.