ClawHub
Back to skill

Security audit

clockify

Security checks for vulnerabilities and agentic risk

Overview

This Clockify skill is a disclosed Maton integration with high-impact automation features, but its sensitive behavior is purpose-aligned and repeatedly gated on explicit user approval.

Install only if you intend to use Maton to access your Clockify account. Review every OAuth connection, write operation, hosted function, trigger, and destination before approving it, especially anything that runs continuously or forwards events to a URL.

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 (1)

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest says this skill is for Clockify API integration and explicitly states Clockify is not an event source. This file documents a separate capability around Notion events, including workspace-wide page content and comment forwarding, which is not justified by the skill's stated Clockify purpose even though the preamble tries to scope its use.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.