ClawHub
Back to skill

Security audit

詹明明·有什么到期了

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed cross-session reminder and tracking aid, with a minor risk that broad trigger phrases could surface saved tracking items unintentionally.

Install only if you want persistent local tracking files for commitments, expiry dates, and in-progress work. Avoid storing sensitive names, amounts, or client details, and consider using explicit /zmm-track invocation because some ordinary phrases may trigger it.

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
Confidence
93% confidence
Finding
The trigger list includes very common phrases such as 'what's due', 'where did we leave off', and similar Chinese equivalents that can appear in ordinary conversation outside an explicit skill invocation. That increases the chance of unintended activation, causing the agent to read or surface cross-session tracking data when the user did not mean to invoke this skill.

Static analysis

No suspicious patterns detected.