ClawHub
Back to skill

Security audit

Target Intelligence Zhcn

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed PatSnap biomedical research helper that uses a user-provided API key for read-only MCP searches.

Install only if you trust PatSnap’s MCP service and are allowed to send your biomedical research queries there. Use a dedicated or scoped API key if possible, avoid sharing logs that contain the MCP URL, monitor quota or billing, and rotate the key if exposed.

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.