Security audit
OpenAI Developer Docs
Security checks across malware telemetry and agentic risk
Overview
This skill is a straightforward helper for querying official OpenAI documentation, with disclosed network use and no hidden persistence or destructive behavior.
Install this if you are comfortable with a local helper script sending documentation searches and requested doc URLs over the network. Keep MCP_URL at the default OpenAI endpoint unless you trust the replacement, and avoid putting secrets or private project details into documentation queries.
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.