Security audit
API Docs Generator
Security checks across malware telemetry and agentic risk
Overview
The available scan context does not show malicious or purpose-mismatched behavior, though VirusTotal was still pending.
Available evidence supports installing as benign with normal caution. Because VirusTotal is pending and no trusted-publisher override applies, users should still review the skill's requested permissions and avoid providing credentials or sensitive data unless those requests are clearly needed for the skill's stated purpose.
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.