Security audit
linkedin-content-creator
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only LinkedIn writing helper that drafts posts and does not execute code, access accounts, or publish content automatically.
Review generated LinkedIn drafts before posting. Do not include confidential company information, customer data, regulated information, private personal details, or unverified claims in prompts or final posts.
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.