ClawHub
Back to skill

Security audit

MaxVideoAI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed MaxVideoAI workflow that uses the provider’s remote service with explicit quote, approval, and recovery safeguards before paid generation.

Install this only if you intend to connect an OpenClaw agent to MaxVideoAI. Before any paid generation, check that the agent shows the exact current quote and waits for your explicit approval; avoid placing credentials, payment details, private bytes, signed URLs, or temporary upload capabilities directly into chat.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description says to use the skill when a user wants 'AI video planning' or 'current model comparison,' which are broad intents that could match many ordinary conversations. While it includes one exclusion example, it does not provide a specific trigger list or clearer constraints on when the skill should not activate.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 8)May include surrounding context.

md
# MaxVideoAI production workflow

Use the authenticated remote MCP connection at `https://api.maxvideoai.com/mcp`
through OpenClaw's supported Streamable HTTP and OAuth flow. Keep credentials
and payment details in the provider's account screens, never in chat or skill
files. A text-only rewrite or an explicit choice of another product does not

Static analysis

No suspicious patterns detected.