ClawHub
Back to skill

Security audit

墨记 (moji-daily)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language daily task tracker that stores tasks locally and provides optional scheduled chat prompts, with no evidence of hidden exfiltration or destructive behavior.

Install this if you want a Chinese-language, chat-driven local task tracker. Before enabling the cron snippets, confirm the Feishu channel is correct and be aware that casual phrases such as adding, canceling, or marking tasks done may update local task Markdown files.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The declared description presents a full daily task management skill with persistent Markdown storage and operational logic for morning review, noon follow-up, evening summary, and ad hoc chat updates. The supplied code chunk merely outputs a static cron configuration snippet for three scheduled prompts. While the schedules align with part of the stated scenario, the actual code does not perform the core claimed functionality. It also hardcodes a Feishu channel, which is an implementation-specific trigger/resource detail not reflected in the declaration. Therefore, the description materially overstates what this code chunk actually does.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill allows broad natural-language phrases like 'XXX做完了', '加一个任务XXX', and '取消XXX' without defining strict invocation boundaries or confirmation rules. In a chat-driven automation context, this can cause ordinary conversation to be misinterpreted as task-management commands, leading to unintended file modifications, task deletion, or silent state changes.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The markdown template is entirely written in Chinese, including headings and task labels, which imposes a specific language on users. There is no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains the operational instructions and all user-facing example prompts exclusively in Chinese, but it does not state that the skill is intended only for Chinese-speaking users or provide any opt-in or language selection mechanism. That can violate language/locale policy because it implicitly forces a specific language on users and agents.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.