Security audit
midjourney
Security checks across malware telemetry and agentic risk
Overview
This skill coherently guides agents to use RunAPI for Midjourney image and video tasks, with expected external API access and credential use disclosed.
Before installing, confirm you trust RunAPI and are comfortable sending prompts, source media URLs, and generated task data to that external service; use an environment API key or explicit CLI login and avoid sharing private media through public URLs unless intended.
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
60/60 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.