ClawHub

F1 CLI

Security checks across malware telemetry and agentic risk

Overview

This is a Formula 1 data helper that documents a third-party CLI and network-backed OpenF1 queries, with no hidden code or persistence found.

Install only if you are comfortable adding the third-party f1 CLI and sending F1-related query parameters to the OpenF1-backed service. Avoid putting personal or sensitive data into raw filters or free-form query values.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger scope is unusually broad and explicitly says even casual F1 questions should invoke the skill, increasing the chance the agent routes general conversation into an external-data skill unnecessarily. In context, that can cause overcollection of user prompts into tool calls, unnecessary network access, and reduced user control over when third-party API-backed retrieval is used.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill is clearly network-backed and supports passing raw query/filter parameters to an external API, but the documentation does not warn that user-supplied values may be transmitted off-box. In this context the data is Formula 1-related and typically low sensitivity, which reduces severity, but hidden external transmission still creates privacy and transparency risks.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal