ClawHub
Back to skill

Security audit

Meme梗图短视频生成器｜AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AI-HIVE video-generation helper that uses user-provided inputs, an API key, and explicit commands for expected media upload, generation, polling, and download workflows.

Before installing, confirm you are comfortable using AI-HIVE, storing or passing an AI_HIVE_API_KEY, and uploading only media you have rights to use. Review generated parameters before running billable generation commands, and avoid pasting real API keys into chat logs or repositories.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill includes executable code paths and instructs use of environment variables, local file access, shell commands, and networked API calls, but it declares no permissions or capability boundaries. This creates a real security risk because an agent may invoke the skill with broader access than users expect, enabling secret exposure, unintended file operations, or external data exfiltration through the AI-HIVE API workflow.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger phrases include broad terms such as social media content and brand rejuvenation concepts that are common in ordinary conversations, which can cause the skill to activate outside the user's actual intent. In a skill with code execution, network access, and potentially billable operations, accidental invocation raises the risk of unnecessary data handling, confusing behavior, or unintended external requests.

Natural-Language Policy Violations

Medium
Confidence
89% confidence
Finding
The default prompt hard-codes Chinese output ('production-ready Chinese workflow') without reflecting user preference or explicit opt-in. This can cause unintended language coercion, reduce usability, and create prompt-level behavior that conflicts with user intent or downstream policy expectations, though it is not a direct code-execution or data-exfiltration issue.

Static analysis

No suspicious patterns detected.