Back to skill

Security audit

Runware Run

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Runware API usage guide with disclosed external API calls and no hidden installation or persistence behavior.

Before installing, make sure you are comfortable with agents using Runware services, uploading selected input files to Runware, and potentially incurring generation costs; the skill itself advises dry-runs or cost reporting before committing to live batches.

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

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.