ClawHub
Back to skill

Security audit

aivideomaker-test-api

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward AIVideoMaker API wrapper, with expected access to your API key and generation task data.

Install this only if you want an agent to use your AIVideoMaker account. Use a dedicated or easily rotated API key, avoid sending sensitive prompts or images unless you trust the provider, and review creation or cancellation requests because they can consume credits or change task state.

SkillSpector

Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Description-Behavior Mismatch

Medium
Confidence
88% confidence
Finding
The examples document a `GET /api/v1/tasks` task-listing capability that is not described in the manifest, creating a hidden or under-declared capability. Undocumented enumeration features can expand the skill's effective permissions and enable unintended access to historical task metadata, prompts, outputs, or identifiers if consumers rely on the manifest for security review and allowlisting.

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/aivideo-client.mjs:5