Swaggerhub
Security checks across malware telemetry and agentic risk
Overview
This is a real SwaggerHub integration, but it gives an agent broad credential-backed ability to change or delete SwaggerHub resources without clear approval guardrails.
Review this skill before installing if your SwaggerHub account can modify shared APIs, domains, or organization settings. Use a least-privileged SwaggerHub/Membrane connection, confirm any create/update/delete request before it runs, and be cautious with the direct proxy feature because it can bypass narrower prebuilt actions.
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
63/63 vendors flagged this skill as clean.