6
Security checks across malware telemetry and agentic risk
Overview
This is a planning-oriented coding skill that asks the agent to compare solution designs before implementation, with no hidden execution, persistence, or sensitive data access in the artifact.
This skill is appropriate to install if you want an agent to spend more time comparing design options before coding. Expect it to produce structured plans and then continue with normal user-directed implementation; review the chosen plan before letting it make broad code changes.
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
66/66 vendors flagged this skill as clean.