Security audit
Human Writing Skills
Security checks across malware telemetry and agentic risk
Overview
This is a writing and editing helper skill with no executable code, credential access, persistence, or hidden data movement in the submitted artifact.
Install this if you want a prose writing and editing workflow. Be aware that some referenced supporting files and commands are not included in the submitted artifact, so parts of the workflow may not work unless supplied elsewhere; also avoid giving it drafts or sources you would not want processed by your agent.
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
62/62 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.