Zoom Out
Security checks across malware telemetry and agentic risk
Overview
This skill is a simple code-understanding prompt that asks the agent to summarize architecture and callers, with no executable code or hidden behavior.
This skill appears safe to install for codebase exploration. It may cause the agent to inspect multiple files in the active project to map architecture and callers, so use it in workspaces where that kind of code reading is appropriate.
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
65/65 vendors flagged this skill as clean.