ClawHub
Back to skill

Security audit

JournalBot Daily Journaling with AI Prompts

Security checks for vulnerabilities and agentic risk

Overview

This is a local journaling helper whose file access is disclosed and fits its purpose, with some overstated feature claims but no evidence of hidden network, persistence, or unsafe behavior.

Before installing, understand that your journal entries may contain sensitive personal information and will be stored in local markdown files, so choose the storage location carefully and back it up if needed. Also treat the advertised pattern detection and reflection features as aspirational or incomplete in this version.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding
The code generally matches the declared local/private journaling purpose: it uses only local filesystem storage, offers daily prompts, supports mood tagging, and provides a simple weekly stats summary. However, the description claims 'weekly reflections' and 'pattern detection,' which are not actually implemented in this code chunk. The only weekly feature is basic aggregate statistics (days written, total words, average words), which is materially less than reflections or pattern analysis. No undeclared risky capabilities or cloud/network access are present.

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
getPrompt() {
    const idx = Math.floor(Date.now() / 86400000) % PROMPTS.length;
    return PROMPTS[idx];
  }

  addEntry(text, mood) {
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Scope Creep

Low
Category
Excessive Agency
Content
**USE AT YOUR OWN RISK.**

- The author(s) are NOT liable for any damages, losses, or consequences arising from 
  the use or misuse of this software — including but not limited to financial loss, 
  data loss, security breaches, business interruption, or any indirect/consequential damages.
- This software does NOT constitute financial, legal, trading, or professional advice.
- Users are solely responsible for evaluating whether this software is suitable for
Confidence
70% confidence
Finding
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Scope Creep

Low
Category
Excessive Agency
Content
**USE AT YOUR OWN RISK.**

- The author(s) are NOT liable for any damages, losses, or consequences arising from 
  the use or misuse of this software — including but not limited to financial loss, 
  data loss, security breaches, business interruption, or any indirect/consequential damages.
- This software does NOT constitute financial, legal, trading, or professional advice.
- Users are solely responsible for evaluating whether this software is suitable for
Confidence
70% confidence
Finding
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Static analysis

No suspicious patterns detected.