ClawHub
Back to skill

Security audit

Habit Tracker

Security checks for vulnerabilities and agentic risk

Overview

The skill is a straightforward habit tracker with disclosed local habit data and reminder behavior, with only minor accidental-activation risk from broad trigger phrases.

Before installing, be aware that habit names, completion history, skips, and reminders may reveal personal routines. Use clear phrasing and confirm any state-changing action if the assistant appears to infer a habit entry from casual conversation.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger phrase at line 8 is short and conversational enough to plausibly match normal user dialogue about habits, which can cause the skill to activate when the user did not explicitly intend to invoke it. While this is not overtly malicious, unintended activation can lead to confusing behavior, incorrect logging of personal habit data, or accidental disclosure/manipulation of locally stored tracking information.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest defines several generic triggers without boundary conditions or explicit invocation requirements, increasing the chance that ordinary conversation will be interpreted as a command. In this skill's context, that could result in accidental habit creation, completion logging, or reminder setup, which undermines user trust and can mishandle personal routine data even if all storage is local.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.