Back to skill

Security audit

Quit Alcohol

Security checks for vulnerabilities and agentic risk

Overview

This is a simple sobriety-support skill with sensitive but clearly purpose-related local tracking and no executable code.

Before installing, treat this as a sensitive personal tracking skill: use it only if you are comfortable keeping sobriety and craving information in your local agent context, and provide coarse location such as city or ZIP code when asking for nearby meetings.

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
  • 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 "alcohol free" is broad and likely to appear in ordinary conversation about drinks, diet, lifestyle, or recovery without a clear intent to invoke this specific skill. In a sensitive sobriety context, accidental activation could lead to unexpected logging, advice, or recovery-oriented responses when the user did not explicitly request them, creating privacy and UX risks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

Offering to "find meetings near me" implies location-based functionality, but the skill does not disclose that location data may be requested, inferred, or processed. Because this skill handles highly sensitive recovery-related behavior, silent or unclear collection of location information could expose private health-adjacent information and reduce informed user consent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.