Back to skill

Security audit

Habit Tracker

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent local habit tracker that writes habit data and optional reports on the user's machine, with no evidence of network access, credential use, hidden execution, or destructive behavior.

Install only if you are comfortable with a local tracker creating and updating habit files under ~/.openclaw/workspace/habits/. Be careful when setting HABIT_DATA_DIR, --data-dir, or --output, because those paths control where files are read or written and report output may overwrite an existing file.

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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill can write local files and read environment-controlled paths, but it declares no explicit tool scope or permissions boundary. That makes its capabilities opaque to the invoking system and increases the chance of unintended file modification or abuse through permissive execution in a broader agent context.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list includes broad natural phrases such as 'habit', 'streak', 'morning routine', and 'did I exercise today', which can match ordinary conversation and invoke the skill unintentionally. In an agent system that can perform file writes, accidental invocation can lead to unwanted logging, habit changes, or report generation without clear user intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This code performs file writes to either the Obsidian vault or a user-provided output path. Although it prints a success message after writing, there is no prior warning or confirmation that an existing file may be overwritten, and the module docstring does not disclose that behavior explicitly.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.