Cinematic Story Video Gen

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:28 PM UTC
• Version:
  0.1.0

Overview

This is a disclosed WeryAI video-generation skill with paid API calls and optional image upload, gated by explicit user approval.

Install only if you intend to use WeryAI and are comfortable providing a WERYAI_API_KEY. Review the full expanded prompt and parameters before approving paid generation, prefer public HTTPS image URLs, and allow local image paths only when you explicitly want that file uploaded to WeryAI.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (3)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 91% confidence
• Finding: The skill declares runtime requirements for an API key, Node.js, and network access, and instructs use of remote WeryAI endpoints, but does not expose an explicit permissions declaration to match those capabilities. This creates a transparency and governance gap: users or platform tooling may underestimate that the skill can access secrets and transmit data off-host, increasing the chance of unintended secret use or data egress.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 94% confidence
• Finding: The skill is presented as a narrowly scoped cinematic-story generator, but the referenced behavior includes broader capabilities such as model enumeration, generic submission flows, task polling, and possible local-file upload to remote storage. That mismatch is security-relevant because operators may trust the skill with more data than intended or approve execution without realizing it can transfer local images and interact with multiple remote endpoints beyond the advertised user story.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The implicit trigger prompts are generic cinematic-language phrases that can match many ordinary media or creative-assistance requests, causing the skill to activate outside its intended scope. This can misroute user requests, invoke external video-generation behavior unexpectedly, and increase the chance of unintended data sharing or tool usage, especially because the skill expands short briefs before submission.

VirusTotal

66/66 vendors flagged this skill as clean.