ClawHub
Back to skill

Security audit

营销图片

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently generates marketing images through AI Hive and its network, file, and API-key behavior is disclosed and aligned with that purpose.

Install only if you are comfortable sending selected reference images and prompts to AI Hive and storing an AI Hive API key locally. Use approved marketing assets, avoid uploading sensitive or unlicensed material, and set --output-dir if you do not want results saved under ~/Downloads/AiHive.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
97% confidence
Finding
The skill instructs the agent to run shell commands, access environment-backed credentials, read local image inputs, write generated outputs, and make outbound network requests, yet it declares no permissions. That mismatch weakens sandboxing and user transparency: an agent may gain broader-than-expected access to files or secrets while contacting an external API, which is especially risky in a skill that processes user-supplied assets.

Static analysis

No suspicious patterns detected.