Security audit
Polar MCP
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed guide for connecting an AI agent to Polar fitness data, with expected privacy risk from OAuth and health or route access.
Install only if you trust the polar-mcp-unofficial npm package and the linked project. Expect the connected agent to access sensitive Polar fitness, sleep, HRV, sample, and possibly route/GPS data after OAuth authentication; avoid exposing token files and revoke Polar access if you stop using it.
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.