ClawHub
Back to skill

Security audit

Runway

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Runway video-production guidance skill; the main caution is confidentiality when sending client or sensitive media to Runway.

Before installing, be aware this skill may guide an agent to send prompts, reference images, or existing footage to Runway. Do not use confidential, client-owned, regulated, or non-consented likeness/performance material unless you have confirmed consent, rights, and the current Runway plan/terms are acceptable for that media.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The file states that Runway trains on user inputs/outputs by default on self-serve plans, but this appears only as a capability note rather than a prominent operational warning in skill guidance. In a production assistant context, users may provide NDA-bound, client, or sensitive footage without realizing it could be retained for model training, creating confidentiality and compliance exposure.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.