ClawHub
Back to skill

Security audit

Network Tox Docking Research Planner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a text-only research planner for network toxicology and docking study designs, with no hidden execution, persistence, or data-access behavior found.

Before installing, understand that the skill may activate for broad chemical-disease research questions and will steer the agent toward a network toxicology plus docking study-plan format. It should be treated as research-planning support, not as clinical, regulatory, or experimental proof of causation.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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
Category
Not specified by scanner
Confidence
98% confidence
Finding

The trigger scope is excessively broad because it activates not only for explicit network toxicology planning requests but also for vague, everyday phrasing such as 'I want to study how chemical X affects disease Y.' This can cause unintended invocation in adjacent contexts, leading the agent to route users into a specialized toxicology-and-docking workflow when they may have intended a general educational, safety, clinical, or unrelated research request.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.