Security audit
Veo
Security checks across malware telemetry and agentic risk
Overview
This appears to be a legitimate Google Veo video-generation skill, but its optional image input can upload any local file path to Google without confirming it is an image.
Install only if you are comfortable sending prompts and selected reference-image files to Google's Veo/Gemini API. Do not let untrusted prompts choose --input-image paths, and avoid using that option unless you have verified the file is a non-sensitive image.
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.