Security audit
gpt
Security checks across malware telemetry and agentic risk
Overview
This skill is a documentation-only RunAPI integration guide for GPT and embedding calls, with no hidden code or persistence.
Install only if you intend to send model and embedding requests through RunAPI. Use a RunAPI-issued key for OPENAI_API_KEY and do not place unrelated OpenAI or other provider credentials there unless you intentionally want that client to send them to the configured RunAPI base URL.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.