Article Writing
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only writing skill that helps draft long-form content and does not request system access, credentials, persistence, or code execution.
Reasonable to install for long-form writing. Treat any voice samples, memos, unpublished drafts, or brand guidance you provide as source material the agent may use for the requested output, and independently verify factual or current claims before publishing.
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.