ClawHub
Back to skill

Security audit

GEO 内容诊断与优化｜AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed AI-HIVE workflow helper that can create briefs and, with user-provided API keys and files, submit image-generation or media-upload tasks; no hidden exfiltration or destructive behavior was found.

Install only if you intend to use AI-HIVE for optional generated assets. Treat API-key setup as sensitive, confirm prompts, routing, batch size, and reference files before running generation, and avoid uploading private or unauthorized media.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill embeds runnable code paths that use environment variables, filesystem access, shell execution, and network access, yet no permissions are declared. This creates a capability-transparency gap: a user or host may invoke the skill believing it performs only content diagnosis, while it can also execute external scripts, access local files, and call remote APIs that may incur cost or expose data.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding
The documented purpose is GEO/AEO diagnosis, but the skill also appears to support broad AI-HIVE capabilities such as generic chat, media generation, uploads/downloads, account/balance access, and interactive API-key setup. This mismatch is dangerous because it can mislead users and orchestration systems about the true trust boundary, enabling unexpected external actions, spending, data transfer, or broader platform access than the description implies.

Static analysis

No suspicious patterns detected.