ClawHub
Back to skill

Security audit

biomarker-investigation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed biomarker research workflow that uses PatSnap life-science MCP services for patents, literature, trials, drugs, and related data.

Install this only if you intend to use PatSnap's external life-science services for biomarker research. Be aware that the setup stores or references your PatSnap API key in the MCP configuration and that queries handled by the skill may be sent to PatSnap MCP services, with web search used only after MCP retrieval is insufficient or current information is requested.

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
90% confidence
Finding
The skill's activation criteria are broad and overlap with many common biomedical research queries, without clearly stating exclusion conditions or narrower triggers. This can cause the skill to load in contexts where its strong procedural instructions, mandatory MCP checks, and patent-risk workflow are not appropriate, increasing the chance of tool overuse, irrelevant data access, or steering the agent away from the user's actual intent.

Static analysis

No suspicious patterns detected.