AI GEO content generator
Security checks across malware telemetry and agentic risk
Overview
This is a transparent, instruction-only content generator that works from user-provided brand knowledge and does not show hidden execution, posting, credential collection, or data exfiltration behavior.
Safe to install as a prompt/template skill. Before using it, remove passwords, tokens, personal data, unreleased strategy, or highly confidential business material from the brand knowledge base, and review all generated public content before publishing.
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.