ClawHub
Back to skill

Security audit

Functions

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a disclosed Browserbase automation setup guide whose sensitive credential use is expected for its purpose, but users should handle those secrets carefully.

Install only if you intend to use Browserbase Functions. Review any pnpm commands before running them, keep Browserbase and login credentials out of git, avoid hardcoding real account passwords, and use test or least-privilege accounts for remote browser automation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly instructs users to copy API credentials into a local .env file and even append them via shell commands, but provides no guidance on secret hygiene such as .gitignore, access controls, or avoiding credential leakage in logs and shells. In a deployment-oriented skill, this omission increases the chance that long-lived API keys are accidentally committed, exposed to other local users, or reused insecurely.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The authenticated automation example collects and uses user email/password credentials and performs remote browser automation, but omits warnings about handling sensitive login data, minimizing retention, or ensuring users understand the trust boundary of the remote execution environment. This can lead operators to pass real credentials into cloud-executed workflows without adequate safeguards, increasing the risk of account compromise or privacy violations.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.