ClawHub
Back to skill

Security audit

imsgctl

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly disclosed helper for reading local Apple Messages data, but users should treat it as privacy-sensitive because it can access message history, attachments, and live activity.

Install only if you want an agent to help inspect local Apple Messages data. Before use, give explicit scope such as the chat, date range, and whether attachments or live monitoring are allowed; avoid broad history reads unless you intend to expose that private content to the agent.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill directly instructs the agent to access highly sensitive local Apple Messages data, including message history, attachment metadata, and live monitoring, without any explicit privacy warning, consent check, or minimization guidance. This creates a real privacy and safety risk because an agent could retrieve or continuously monitor personal communications from the local machine in response to ambiguous or insufficiently authorized requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.