ClawHub
Back to skill

Security audit

Blog to Avatar Video

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims: it sends a user-provided blog URL and avatar information to Revid to generate a talking-head video.

Install only if you trust Revid with the blog content and avatar image links you provide. Treat REVID_API_KEY as a secret, avoid private or access-controlled URLs unless authorized, and ensure you have rights to use any avatar image or likeness.

SkillSpector

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
91% confidence
Finding
The skill sends user-supplied blog URLs and avatar image URLs to Revid's third-party service, but the user-facing description does not clearly disclose that external transmission occurs. This can cause users to unknowingly share potentially sensitive URLs, private intranet links, or personal images with an outside provider, creating privacy and compliance risk.

Natural-Language Policy Violations

Medium
Confidence
82% confidence
Finding
The payload hard-codes `voiceId: aria-en-us` and `language: en-US` as defaults without making user choice or consent prominent. While not a direct exploit vector, this can mis-handle user content, create incorrect outputs for other languages/personas, and may lead to unexpected processing of content under the wrong locale or identity assumptions.

Static analysis

No suspicious patterns detected.