Security audit
SeeVido Video Prompt Architect
Security checks across malware telemetry and agentic risk
Overview
This is a text-only video prompt workflow with an optional, disclosed read-only MCP helper and no evidence of hidden data access or destructive behavior.
Installing the skill itself is low risk. Only enable the optional MCP if you are comfortable running a GitHub-hosted npx package and adding it to your MCP configuration; review or pin the source if you need stricter supply-chain control.
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.
Static analysis
No suspicious patterns detected.