Security audit
Ai Content Audit
Security checks across malware telemetry and agentic risk
Overview
This is a prompt-only content-audit skill with no code execution, hidden persistence, or unrelated data access.
This appears safe to install as a writing and content strategy aid. Before using it, only provide content libraries, analytics, or performance data you are comfortable sharing with the agent, and treat delete-or-redirect recommendations as decisions to review before acting.
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.