Security audit
Writing Style And Tone
Security checks across malware telemetry and agentic risk
Overview
This writing-style skill provides disclosed drafting and editing guidance with human approval and no executable or background behavior.
Before installing, note that the skill is intended to shape drafts that may later be published through other workflow skills; keep the stated human review step, verify factual claims and statistics before use, and do not let it invent personal stories or credentials.
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.