ClawHub

Concept2-logbook

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Concept2 workout-analysis helper, but users should treat its API token and fitness data as sensitive.

Install this only if you intend to connect a Concept2 Logbook account. Use a revocable API token, avoid pasting tokens into shared logs or transcripts, and protect any JSON exports because they may include personal workout, heart-rate, and profile information.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill clearly documents network access to external Concept2 API endpoints, yet the manifest shown in the file does not declare any permissions or equivalent capability boundary. That mismatch weakens reviewability and user consent because a caller may not understand that the skill will transmit authentication tokens and workout data off-platform.

Vague Triggers

Medium
Confidence
79% confidence
Finding
The description is broad enough to match many generic workout-analysis requests, increasing the chance the skill is invoked in contexts where the user did not intend external account access or API-backed processing. Over-broad activation can lead to unnecessary exposure of fitness history, profile data, or tokens when a more limited local-analysis skill would have sufficed.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The document instructs use of an API access token and describes reading user profile data such as birthdate, but it provides no privacy warning, retention guidance, or handling restrictions. This creates a real risk of sensitive health-adjacent data and credentials being collected, logged, or reused without informed consent or minimization.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal