Security audit
Runware Prompting
Security checks across malware telemetry and agentic risk
Overview
This skill is a plain prompting guide for Runware image and video models and does not add hidden execution, persistence, or data access.
This skill appears safe to install as a Runware prompting reference. Users should still remember that any downstream Runware model calls or related skills may involve provider APIs, generated media costs, or web grounding depending on the model settings they choose.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.