Security audit
Don Corleone Writing Style
Security checks across malware telemetry and agentic risk
Overview
This is a text-only writing style skill with disclosed professional tone guardrails and no code, credentials, persistence, or external access.
Safe to install as a style-only prompt. Review generated messages before sending because the style is intentionally firm and authority-heavy, and avoid using the anti-AI writing guidance to misrepresent authorship where disclosure is required.
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.