Security audit
sdk
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only RunAPI SDK guidance skill with expected API-key advice and no executable behavior.
Safe to install if you want guidance for integrating RunAPI SDKs. Treat RUNAPI_API_KEY as a real secret, review any SDK packages before adding them to production, and use the RunAPI CLI or a model-specific skill instead for one-off media tasks.
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.
Static analysis
No suspicious patterns detected.