Security audit
Text Post And Microblog
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed writing guide for text posts and microblogs, with no hidden execution, credential access, or persistence found.
Installers should still review any post before publishing, verify volatile platform statistics, and ensure they have consent before featuring people or making sensitive financial or health-related claims.
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.
Static analysis
No suspicious patterns detected.