ClawHub
Back to skill

Security audit

Dida365

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward TickTick/Dida365 task-management helper, with disclosed read and write task actions but no hidden code or persistence.

Before installing, make sure you want the agent to use your TickTick/Dida365 account for task requests. For generic task-management prompts, confirm which task system should be used, and review any create, batch update, move, or complete action before allowing it to run.

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
  • 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
Findings (3)

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The invocation description is overly broad because it says to invoke the skill for 'their tasks, to-do lists, projects ... or anything about their task management workflow, even if they don't say TickTick explicitly.' That can route generic task-related requests into a skill with read/write access to a specific external account, increasing the chance of unintended data access or task modification in the wrong system.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill prominently documents create, update, move, and complete-task capabilities but does not warn that these actions modify persistent user data in their TickTick/Dida365 account. In a tool-using agent context, missing mutation warnings can lead to silent or surprising state changes if the skill is invoked automatically or the user intended only to view information.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
75% confidence
Finding

The file presents user-facing capability descriptions in Chinese alongside English headings and instructions, but it does not state whether the skill should respond in Chinese, English, or according to user preference. This can create an implicit language/locale assumption without opt-in.

Content

No source excerpt is available for this finding.