Security audit
de-ai-outline
Security checks across malware telemetry and agentic risk
Overview
This skill is a focused writing-style helper for making outlines and presentation drafts sound less AI-generated, with no hidden execution or data access behavior found.
Before installing, understand that this skill is intended to rewrite tone and presentation wording. Review outputs for factual preservation and choose the register tier carefully, especially for formal or executive-facing materials.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.