ClawHub
Back to skill

Security audit

todo-list-promax

Security checks for vulnerabilities and agentic risk

Overview

This is a local personal todo/reminder skill with disclosed storage and opt-in reminders; the main caution is that it may save messages and attachments when users use natural reminder phrases.

Install only if you want a persistent local todo assistant that may retain the full source message and attachments for saved todos. Review saved items if messages may contain sensitive information, and enable the daily cron reminder only after confirming you want background reminders.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill defines several activation phrases that are common in ordinary conversation, such as '提醒我', '记一下', '别忘了', and their English equivalents like 'remind me to' and 'don't forget'. This can cause unintended persistence of user content, attachment capture, and later reminders without sufficiently explicit user intent, which is especially risky because the skill permanently stores source messages and may create scheduled reminders.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.