Krea AI
Security checks across malware telemetry and agentic risk
Overview
This skill is a straightforward Krea image-generation helper that uses a disclosed API token and does not include executable code or hidden persistence.
Install this only if you are comfortable giving the agent a Krea API token and sending prompts or referenced image URLs to Krea. Prefer a revocable token and avoid confidential prompts or private image URLs unless that fits your data policy.
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.