ClawHub
Back to skill

Security audit

Fitness Log

Security checks across malware telemetry and agentic risk

Overview

This is a local fitness tracker, but its script can turn crafted workout inputs into unintended local Python execution.

Review before installing. The skill has a coherent local-only fitness purpose and no network or credential behavior, but do not pass untrusted or unusual text into its commands until the script is fixed to pass values safely to Python through arguments, environment variables, or JSON serialization. Also be aware that workout and weight data remain stored locally in $HOME/.fitness.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The description says 'Use when you need Fitness Log capabilities,' which does not define concrete trigger phrases or boundaries for when the skill should activate. This is ambiguous and could overlap with many general health or productivity requests, increasing the risk of unintended invocation.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.