Security audit
BasedAgents
Security checks across malware telemetry and agentic risk
Overview
This skill is a clearly described BasedAgents integration, with expected external service and keypair use disclosed for its registry, scanning, messaging, and task features.
Install this only if you trust BasedAgents and the npm MCP package it runs. Avoid scanning private packages, repositories, or internal MCP endpoints unless you are authorized and comfortable sending those target details to BasedAgents services. Configure a keypair only when you need signed messaging or task marketplace actions, and review those actions before approving them.
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.