If you vanished today (quiet home → feed moves on)

• Outcome: Pass
• Latest audit: Sep 14, 2026 · 10:23 PM UTC
• Version: 1.0.1

Overview

This skill is a disclosed WeryAI video-generation helper for a specific melancholic short-video format, with no hidden persistence or unrelated local data access found.

Install only if you are comfortable sending prompts, public HTTPS image URLs, and your WeryAI API key to WeryAI for paid video generation. Use it deliberately for the absence-short template, avoid private image URLs, and specify subtitle language if English is not desired.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• 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
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (7)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence
• Finding: The skill is presented as a narrowly themed, safety-bounded 'absence shorts' generator, but the documented workflow and model options enable broad text/image/multi-image video generation via a remote API. This mismatch is dangerous because reviewers and users may trust a constrained emotional-content tool while it actually provides materially wider generative and networked capability than advertised.

Ae1

High

• Category: analysis-evasion

Content

- **API hosts** fixed in `video_gen.js`.

• Confidence: 100% confidence
• Finding: Referenced artifact was not completely inspected

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 91% confidence
• Finding: The skill declares network and environment-variable dependent behavior through metadata and CLI usage, but does not define explicit tool scope such as allowed-tools or permissions. That creates an authorization and review gap: the runtime may still permit external API calls using a secret key without the least-privilege boundaries expected by users or platform policy.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The description says to use the skill when the user wants "melancholic mood" or "lonely-apartment" vibes, which are broad emotional contexts rather than specific task triggers. This can overlap with common creative or conversational requests and may cause unintended invocation because the scope is not narrowly bounded by explicit trigger phrases or exclusion examples.

Natural-Language Policy Violations

Medium

• Confidence: 94% confidence
• Finding: The file states "English subtitles" as a default output requirement rather than offering language choice first. That creates a language policy concern because it imposes a specific language unless the user explicitly overrides it.

Natural-Language Policy Violations

Medium

• Confidence: 96% confidence
• Finding: The typography instructions require "English on screen," which is a direct locale/language constraint. This is a natural-language policy violation because it mandates one language without documenting user choice or a justified regional limitation.

Natural-Language Policy Violations

Medium

• Confidence: 91% confidence
• Finding: This file contains its primary CLI description, commands, examples, and environment-variable guidance in Chinese only. The policy requires flagging language or locale constraints when the skill forces a specific language without user opt-in, and no alternative language or selection mechanism is offered here.

Static analysis

No suspicious patterns detected.