ClawHub
Back to skill

Security audit

scarcest-not-money-video-gen

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed WeryAI video-generation helper that uses a paid API key and may upload user-selected images, but I did not find hidden persistence, destructive behavior, or undisclosed data access.

Install only if you are comfortable using WeryAI with a paid API key and sending prompts and selected image inputs to WeryAI. Prefer public HTTPS image URLs; do not provide local file paths unless you have verified the exact file and explicitly approve uploading it.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
82% confidence
Finding
The skill declares no explicit permissions while clearly requiring environment-secret access and outbound network use. This weakens transparency and reviewability, making it easier for users or hosting platforms to invoke a capability-bearing skill without understanding that it can access API keys and send data to external services.

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding
The documented purpose is narrowly framed, but the referenced behavior is much broader: generic video generation, arbitrary task/status operations, and possible local file upload to a third party. This mismatch is dangerous because reviewers and users may trust the narrow description while the actual skill can process unrelated prompts and exfiltrate local content if the script supports file-path uploads.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The implicit trigger prompts are semantically broad enough to match generic short-form video requests beyond the intended niche, which can cause the skill to activate unexpectedly. Overbroad invocation increases the chance of prompt routing errors, user surprise, and accidental application of this skill’s opinionated output structure in unrelated contexts.

Static analysis

No suspicious patterns detected.