ClawHub
Back to skill

Security audit

电商TVC广告片工作室｜AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AI-HIVE advertising video workflow with expected API, media upload, download, and local editing helpers.

Install only if you intend to use AI-HIVE for ad video production. Treat generated commands as manual steps, review prompts and routing before running billable tasks, upload only media you are authorized to use, and keep the AI-HIVE API key out of logs and shared files.

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 operational guidance for environment variables, filesystem access, network calls, and shell execution, but does not declare corresponding permissions. That mismatch weakens security review and user consent because an agent may invoke higher-risk capabilities without an explicit permission contract. In this context, the danger is elevated by support for API-key handling, uploads, downloads, and local media processing, which can expose secrets or modify local files if the runtime auto-executes examples or companion scripts.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill enables implicit invocation without tightly constraining when it may activate, which can cause the agent to trigger this ad-production workflow in situations the user did not clearly request. Because the skill can steer requests into production workflows and runnable AI-HIVE commands, unintended activation could lead to unnecessary external actions, confusion about user intent, or execution of costly or risky media-generation steps.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The default prompt hardcodes Chinese output and does not indicate that this behavior depends on user preference or locale. This can override user expectations, degrade transparency, and increase the chance that users approve or execute generated commands they do not fully understand, especially in a workflow that produces runnable instructions for external systems.

Static analysis

No suspicious patterns detected.