Back to skill

Security audit

Reminder

Security checks for vulnerabilities and agentic risk

Overview

This reminder skill is mostly coherent, but it can create persistent cron-based Telegram reminders from broad natural-language mentions without a clear explicit confirmation step.

Install only if you want an assistant that may save reminder data and create Telegram cron notifications. Use explicit phrases like 'remind me' or 'schedule this', and review or cancel cron jobs if a casual mention is captured unintentionally.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill summary/description is broad enough that an agent could invoke it on ordinary conversation about plans, meetings, or schedules without a clear user intent to persist data or schedule Telegram notifications. That creates a real risk of over-triggering a stateful skill that writes to workspace files and creates cron jobs, which can cause unintended data storage and message delivery.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The capture examples show natural-language utterances that look like normal conversational statements, but they are not constrained by explicit trigger rules or consent requirements. In context, this can cause the assistant to interpret casual mentions of future events as commands, leading to unintended reminder creation and downstream cron scheduling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The comment sets the default locale-related behavior to Asia/Shanghai, which can be a language/locale policy concern when applied implicitly. The file does not indicate that users can choose the default at setup time beyond an environment override, nor does it justify why this specific regional default is required.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.