ClawHub
Back to skill

Security audit

Smoking (Tracker, Logger, Quit, Reduce)

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only smoking and nicotine tracking skill that stores user-approved local notes but does not run code, call external services, or request credentials.

Install only if you are comfortable keeping smoking, nicotine-use, trigger, and plan notes in local files under ~/smoking/. Review or delete those files if you no longer want the history retained, and use licensed medical support for medication, pregnancy, severe symptoms, or mental-health crises.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Anti-Refusal Statement

High
Category
Anti-Refusal
Content
## When to Use

User wants to log tobacco or nicotine use, reduce consumption, quit smoking, or keep structured records without judgment.
Agent tracks baseline behavior, applies the right mode (`logger`, `reduce`, or `quit`), and keeps progress measurable with practical next steps.

## Architecture
Confidence
80% confidence
Finding
Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The instruction 'Use for users in `quit` mode' does not define what 'quit mode' means, when the skill should activate, or what distinguishes it from nearby intents. Because the trigger scope is not specific and provides no exclusion examples, it could cause unintended invocation for loosely related conversations about quitting or stopping something.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs the agent to store smoking and nicotine-use behavior data, trigger patterns, and plan status, but it provides no user-facing consent, notice, retention limits, or control over that storage. Because this is sensitive health-related behavioral data, silent persistence increases privacy risk and can expose users to profiling or unintended disclosure if the data is later accessed, reused, or mishandled.

Static analysis

No suspicious patterns detected.