Agentic Coding
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only coding workflow skill with disclosed local notes and no executable payload or hidden data flow.
Reasonable to install if you want a stricter AI coding workflow. Before enabling its opt-in memory, review what may be written under ~/agentic-coding/ and keep task contracts narrow so code changes stay within an agreed scope.
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.