ClawHub
Back to skill

Security audit

Logistics Tracker

Security checks across malware telemetry and agentic risk

Overview

This skill appears to support a legitimate API integration, but it handles the user's Track123 API key in an unsafe way by asking for it in chat and storing it in the skill file.

Review before installing. Only use this skill if you are comfortable configuring a Track123 API key, and prefer moving the key to a secure secret store or environment variable instead of pasting it into chat or saving it in SKILL.md. Rotate the key if it has already been shared this way.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

Medium
Confidence
96% confidence
Finding
The skill directs the agent to solicit a third-party API secret from the user and persist it by modifying the skill file, which creates an unnecessary credential collection and storage path. Embedding secrets into prompt-managed files increases the chance of later disclosure, reuse in unrelated contexts, and unauthorized access to the Track123 account.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill explicitly instructs the user to paste an API key into the skill file without any warning or guardrails around credential handling. This normalizes unsafe secret sharing and may expose the key in chat logs, versioned files, debugging output, or subsequent model context.

VirusTotal

53/53 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.