ClawHub
Back to skill

Security audit

pharmaceuticals-exploration

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed PatSnap pharmaceutical research assistant that uses configured life-science MCP services and web search only as a research fallback.

Install this only if you intend to use PatSnap life-science services for pharmaceutical research. Your drug, disease, target, trial, patent, and deal queries may be sent to PatSnap MCP services, and the API key used in setup should be protected like any other secret.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The activation guidance is broad enough to trigger on many generic drug, disease, or target-related queries, including indirect invocation via other skills. Over-broad activation can cause unnecessary access to sensitive external data sources and unintended delegation, increasing the attack surface for prompt injection, data over-collection, and tool misuse in multi-skill workflows.

Static analysis

No suspicious patterns detected.