ClawHub
Back to skill

Security audit

Research Automation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed web-research workflow that saves markdown research notes, with no executable code or hidden install behavior found.

Before installing, be aware that running the skill can perform web research and create persistent markdown files in the workspace, and enabling heartbeat entries can repeat that behavior on a schedule. Review the generated health-related findings critically and do not treat protocol or dosing content as professional medical guidance.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly states it auto-saves research outputs into workspace files, but it does not clearly warn users up front that invoking the skill will write persistent artifacts and may generate derivative content files. This can lead to unexpected data creation, workspace pollution, and accidental retention of potentially sensitive or compliance-relevant material gathered from web research.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The heartbeat section describes autonomous recurring execution that performs web activity and writes files, but it lacks a clear warning about ongoing background behavior, frequency, storage effects, and operator consent. Scheduled execution increases risk because repeated network access and file creation can continue without active user awareness, causing surprise costs, noisy outputs, or unintended collection and retention of material over time.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.