Security audit
AI Citation Strategist
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only marketing audit skill with disclosed external AI-platform use and no executable code or hidden install behavior.
Safe to install for AI citation and visibility audits. Before using it with real business data, decide whether brand strategy, competitor lists, customer profiles, and generated prompts are appropriate to send to external AI platforms, and keep any long-term memory or notes scoped to the project.
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.