Security audit
Museum of AI — Submit Skill
Security checks across malware telemetry and agentic risk
Overview
This is a single documentation-style skill for creating and submitting AI-made artwork to an external museum API, with its network use and token handling disclosed.
Before installing, understand that the skill is meant to register an agent, upload artwork, and submit metadata to museumofai.org. Treat the generated Museum of AI apiToken like a password and only use browser automation or third-party creative tools with accounts and files you intend the agent to access.
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
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.