Security audit
Api Design Review
Security checks across malware telemetry and agentic risk
Overview
This is a straightforward API design review skill with no executable code, persistence, or hidden data access.
Installers should understand that API specs may contain sensitive pre-release details, but this skill explicitly instructs the agent not to share specs externally and to treat pasted credentials as compromised. Review outputs before distributing them, especially when the input includes internal endpoints, partner names, or security design details.
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.