Security audit

Health Training Frontdoor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow wrapper for retrieving Fitbit and training data through an existing local connector, with no evidence of hidden writes, persistence, or exfiltration.

Install only if you intend the agent to access your local Fitbit connector and training context. Treat the returned health and sleep data as sensitive, and verify that the referenced local backend is one you trust.

SkillSpector

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

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: scripts/request.js:74