Security audit
Prompt Engineering
Security checks across malware telemetry and agentic risk
Overview
This is a coherent prompt-engineering guide for inference.sh, with disclosed CLI setup and examples, but users should treat the installer and external model calls with normal caution.
Install only if you trust inference.sh and are comfortable authenticating its CLI. Prefer manual download or checksum verification instead of piping a remote script into sh, and avoid putting secrets or sensitive private data into prompts sent to external model providers.
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.