Back to skill

Security audit

Reminder

Security checks for vulnerabilities and agentic risk

Overview

This is a simple reminder skill that clearly stores reminder data locally and schedules Telegram reminders, with no hidden code or unrelated behavior found.

Install this only if you are comfortable having reminder details saved in your OpenClaw workspace and used to create Telegram reminder jobs. Set REMINDER_TZ if you are not using Asia/Shanghai, and verify important reminder times after scheduling.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The invocation text is broad enough that ordinary conversation about meetings, plans, or schedules could trigger the skill without a clearly bounded user request. In this skill's context, that matters because activation can lead to persistence of personal event data in the workspace and scheduling outbound Telegram notifications, creating privacy and action-without-clear-intent risk.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill describes storing reminders in the workspace and sending Telegram notifications, but it does not clearly warn users that personal schedule data will be persisted and transmitted. That omission can cause users to disclose sensitive events, locations, birthdays, or deadlines without informed consent, increasing privacy and data-handling risk.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
Defaulting to `Asia/Shanghai` and Chinese-oriented date interpretation without clear opt-in can silently misinterpret dates and times for users in other locales. In a reminder skill, that can cause reminders to fire at incorrect times or on incorrect dates, which is operationally harmful even if it is not a classic confidentiality breach.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The comment sets a default timezone of Asia/Shanghai via REMINDER_TZ, which imposes a specific locale choice if the environment variable is not provided. This can violate language/locale policy because the file does not indicate user opt-in or explain why this region-specific default is required.

Static analysis

No suspicious patterns detected.