ClawHub
Back to skill

Security audit

Embase

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Embase read-only connector that uses OOMOL's CLI for article search and retrieval.

Install this if you want an agent to use your OOMOL-connected Embase account for biomedical literature searches and article retrieval. Review the OOMOL CLI installation and account connection steps before first use, and do not connect an Embase account unless you are comfortable with OOMOL brokering those requests.

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
91% confidence
Finding
The manifest tells the agent to use this skill for "ANY Embase request" with no scope boundaries, exclusions, or routing constraints. Overly broad trigger language can cause the agent to invoke this skill for unintended prompts, increasing the chance of unnecessary external data access, privacy leakage, or bypass of more appropriate controls for edge-case requests.

Static analysis

No suspicious patterns detected.