Security audit

Mindfulness (Tracker, Logger, Guided Practice)

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent local mindfulness coaching skill that stores optional practice notes only after user confirmation and does not request network, credential, or executable authority.

Before installing, be aware that this skill may keep mindfulness session logs, mood or state ratings, routine plans, and recommendation notes in ~/mindfulness/. Use the setup preferences to limit when it activates, disable proactive suggestions if unwanted, and only approve local file writes you are comfortable retaining.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The 'When to Use' section describes activation in broad natural language such as 'User wants a complete mindfulness support system' and 'Agent handles session guidance' without defining concrete trigger phrases, scope limits, or exclusion cases. This can overlap with many general wellness or reflection requests and may cause unintended invocation.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The activation guidance is broad enough to trigger on common conversational topics like stress, focus, or emotional regulation, which can cause the skill to engage when the user did not intend it. In a skill that stores behavioral preferences and logs, unintended activation increases the risk of collecting sensitive wellness-related data without clear, context-specific consent.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill describes storing ongoing user state, baseline patterns, and recommendation outcomes, but does not pair that with a prominent user-facing disclosure about what is retained, for how long, and under what control. Because this concerns potentially sensitive mental wellness and behavioral data, silent or poorly explained retention can undermine privacy expectations and lead to overcollection.

Static analysis

No suspicious patterns detected.