I2I
Security checks across malware telemetry and agentic risk
Overview
This is a non-executable placeholder skill that tells the agent to be transparent that image-to-image support is not implemented yet.
Safe to install as a placeholder, but do not expect it to generate images yet. Before relying on a future implementation, check that it documents the real endpoint, image upload method, credentials, network calls, polling behavior, and user controls.
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
65/65 vendors flagged this skill as clean.