ClawHub
Back to skill

Security audit

Auto video clipping and publishing | by Vizard.ai

Security checks for vulnerabilities and agentic risk

Overview

This Vizard.ai skill is mostly coherent, but it can post videos to real connected social accounts without clearly requiring user confirmation first.

Install only if you intend to use Vizard.ai with your own API key and are comfortable sending video content to Vizard. Before any publish-video call, require the agent to show the selected clip, target social account, caption or title, and publish time, then get explicit approval.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill description is broad enough to activate on generic video-editing or social-media automation requests, even when the user did not specifically ask to use Vizard.ai. That can route user content to an external third-party service unnecessarily, increasing the chance of unintended data transfer and API-backed actions outside the user's expectations.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill includes a publish-to-social workflow without an explicit warning that it can post to connected external accounts. In an agent context, this creates a real risk of unauthorized or accidental publication, which can cause reputational harm, privacy leakage, or unintended public disclosure.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documentation exposes a capability to publish directly to connected social media accounts and states that omitting `publishTime` causes immediate publication, but it does not include any warning, confirmation requirement, or safety guidance. In an agent skill context, this increases the risk of unintended or unauthorized posting, reputational harm, and misuse if an agent invokes the endpoint without explicit user confirmation.

Static analysis

No suspicious patterns detected.