Security audit
loop-builder
Security checks across malware telemetry and agentic risk
Overview
This skill is a workflow-design helper that emphasizes user confirmation, bounded iteration, and human approval before risky actions.
This appears safe to install as a workflow-planning skill. Users should still review any generated Loop, Agent, or Skill package before using it, especially where it proposes durable state, file edits, installation, publication, production changes, deletion, billing, credentials, or other high-impact actions, because those later actions require separate approval and should stay narrowly scoped.
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
60/60 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.