ClawHub
Back to skill

Security audit

Worthtotry Skill

Security checks across malware telemetry and agentic risk

Overview

The skill mostly does what it claims, but its fallback REST workflow asks users to give the agent an access token without enough safety guidance.

Install only if you are comfortable with WorthToTry receiving the product URL and owner email. Prefer the OAuth/MCP path where the agent never handles an access token. If you use the REST fallback, provide only a minimal token through a secure secret mechanism if available, avoid pasting it into normal chat, and revoke it after the task.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The README describes that the agent performs a POST with the product URL and the user's email address, but it does not present this as an explicit privacy/data-sharing warning before use. That omission can lead users to disclose personal or business contact information to a third-party service without informed consent, which is especially relevant because this skill is designed for one-line installation and fast submission.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The document explicitly instructs the agent to ask the user for a personal access token, but it does not include any warning to avoid exposing, logging, storing, or reusing that credential beyond the immediate request. In an agent/skill context, prompting users to paste bearer tokens into chat materially increases the risk of credential leakage through transcripts, logs, or downstream tooling.

Credential Access

High
Category
Privilege Escalation
Content
## Authentication

Reads need nothing. Writes need `Authorization: Bearer <token>`, where the token is a personal
access token the person creates in their dashboard. Ask them for one; do not try to mint it.

The same ceiling applies here. Nothing in this API publishes a listing, sets a launch date, or takes
a payment.
Confidence
94% confidence
Finding
access token

VirusTotal

52/52 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.