ClawHub
Back to skill

Security audit

短剧批量生产流水线｜AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AI-HIVE short-video production helper whose network, file, credential, and media-processing behavior matches its stated purpose.

Install only if you are comfortable providing an AI-HIVE API key and uploading the selected media assets to AI-HIVE. Review prompts and routing before billable generation, keep API keys out of chats and logs, and specify a non-Chinese output language if needed.

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill exposes operational capabilities including environment-variable access, file read/write, network access, and shell execution, but does not declare permissions or constrain their use. This creates a trust and review gap: users or platforms may treat the skill as low-risk while it can perform sensitive local and remote actions, increasing the chance of unintended data access, secret leakage, or unsafe command execution through helper scripts.

Tp4

High
Category
MCP Tool Poisoning
Confidence
89% confidence
Finding
The documented purpose is a narrow short-drama production workflow, but the skill apparently includes broader capabilities such as generic AI chat, model and user-info retrieval, arbitrary file upload, and standalone ffmpeg media manipulation. That mismatch is dangerous because it expands the attack surface beyond user expectations, enabling data exfiltration, misuse of uploaded local files, or execution of unrelated actions under the cover of an apparently specialized workflow.

Natural-Language Policy Violations

Medium
Confidence
87% confidence
Finding
The default prompt hard-codes Chinese output ('production-ready Chinese workflow') regardless of the user's preferred language, which can override user intent and reduce transparency about what the agent will produce. In a production workflow skill, this can cause user confusion, downstream misuse, or accidental policy/compliance mismatches if operators expect output in another language.

Static analysis

No suspicious patterns detected.