Back to skill

Security audit

Habit Checkin

Security checks for vulnerabilities and agentic risk

Overview

This is a simple habit check-in skill with disclosed local storage, but it should be clearer about broad triggers and the unrelated video notes in its documentation.

Before installing, be aware that habit check-ins may be stored persistently in a local JSON file. Prefer using the explicit habit-checkin trigger and remove the unrelated B站 notes if you want cleaner, less confusing skill documentation.

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
  • 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documentation discloses that data is stored in a local JSON file, but it does not warn users that their check-in history will persist on disk. In a habit-tracking context, this can expose behavioral data to other local users or create privacy surprises, especially when combined with broad triggers that may record activity unintentionally.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases include very common expressions such as 打卡, 签到, 今天打卡, and check in, which can occur in ordinary conversation outside the intended habit-tracking context. This can cause unintended invocation of the skill, leading to unexpected writes to the local habit data file and confusing or privacy-impacting behavior.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest and earlier documentation describe a simple habit tracking skill for daily check-ins and streak counting, but lines L30-L63 switch to 'B站学习' content listing unrelated videos and download-link resources. This is not merely extra detail; it actively changes the apparent intent of the file from skill documentation to media/resource curation unrelated to habit tracking.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.