ClawHub

AI Video

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a disclosed video-generation API helper, but one included helper can send the configured API key to a user-supplied URL outside the intended provider.

Install only if you intend to provide a skills.video API key and send generation prompts to that service. Use the default open.skills.video endpoints, avoid untrusted OpenAPI files or prompts that supply full URLs, keep the key in scoped skill configuration instead of a shell profile when possible, and monitor credit usage.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill explicitly instructs use of environment variables, local files, network requests, and shell commands, yet it does not declare permissions for those capabilities. This creates a trust and containment gap: a host may expose sensitive execution capabilities without clear consent boundaries, increasing the risk of unintended API calls, file access, or command execution if the skill or its supporting scripts are modified or abused.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The default prompt uses a very broad trigger phrase, 'Use $ai-video to create videos of {subject},' without narrowing when the skill should be invoked or what kinds of requests are in scope. This can cause over-invocation or invocation in ambiguous contexts, increasing the chance that the agent calls an external video-generation capability when not clearly intended by the user, which may lead to unsafe content generation, privacy issues, or unintended external API use.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal