ClawHub
Back to skill

Security audit

Rehub

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small Markdown-only integration that openly points agents to an external Rehub API, with privacy documentation gaps but no hidden code or local system access.

Before installing, treat this as a remote-service integration: use it only when you are comfortable with visit/activity data and generated question-answer content being sent to or produced by the Rehub service. Avoid using it with sensitive prompts or private workspace data unless the publisher provides clearer data-retention and operator details.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly sends interaction data to an external service, including recording visits and returning generated question/answer content, but provides no user-facing warning, consent step, or data handling disclosure. This is dangerous because an agent or user may unknowingly transmit prompts, generated content, usage metadata, or behavioral information to a third-party endpoint, creating privacy, compliance, and data-governance risks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.