Howto Docs
Security checks across malware telemetry and agentic risk
Overview
The reviewed artifacts appear purpose-aligned and scanner-clean, with no evidence of hidden data theft, destructive behavior, or deceptive instructions.
Install only if you want these developer/maintainer workflows. Expect the agent to read project files and, for some tasks, run local commands or use configured GitHub/Convex/ClawHub credentials; review high-impact commands before allowing moderation, publishing, or broad review-helper execution.
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.