AI Opportunity Radar — Discover What In Your Life Should Be Automated

• Outcome: Pass
• Latest audit: Sep 11, 2026 · 1:40 PM UTC
• Version: 2.0.1

Overview

This is a chat-based reflection skill that asks scheduled check-ins and remembers routine patterns, with no code, network access, credentials, or hidden execution behavior found.

Install this only if you are comfortable sharing routine, workflow, and frustration patterns for ongoing reflection. Avoid including sensitive personal, health, financial, or confidential work details unless you intend the chat assistant to use them for pattern analysis; ask how to pause scheduled check-ins or clear stored observations if your platform supports it.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Anti-Refusal Statement

High

• Category: Anti-Refusal
• Confidence: 92% confidence

Finding

The instruction to 'NEVER ignore a user message' is an anti-refusal pattern because it pressures the agent to always comply rather than safely decline harmful, policy-violating, or manipulative requests. In a conversational companion skill, this can weaken safety boundaries by discouraging refusal, escalation, or disengagement when the user asks for unsafe content or attempts prompt abuse.

Content

Scanner excerpt · prompt.md (reported line 31)May include surrounding context.

md

# Conversation Rules (CRITICAL)

## Always Respond

You must NEVER ignore a user message.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 91% confidence

Finding

The skill description is framed in broad, ambient language ('discover what in your life could be automated through casual daily conversations') without defining when the skill is active, what inputs it monitors, or what boundaries apply. This can cause users to over-share personal routine information under the impression of informal chatting, enabling unintended collection and analysis of sensitive behavioral data over time.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The skill states that the AI 'observes patterns' and surfaces automation opportunities over time, but it does not warn users that personal routines, frustrations, and workflow details may be retained or analyzed longitudinally. This omission is dangerous because the skill's core function depends on aggregating behavioral signals across conversations, which can reveal sensitive lifestyle, work, health, or relationship patterns even when each individual message seems harmless.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 93% confidence

Finding

The installation instructions encourage recurring scheduled check-ins and reflections that imply persistent conversational monitoring, but they do not specify consent boundaries, pause/disable controls, or limits on what conversation content is analyzed. In a skill explicitly designed to observe patterns over time, this ambiguity increases the risk of silent long-term profiling of habits, routines, and other personal data.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 90% confidence

Finding

The description advertises an always-on, broadly scoped conversational role for discovering automation opportunities through casual daily conversations, but it does not define boundaries, activation conditions, or limits on what kinds of user interactions should trigger analysis. In a skill that observes lifestyle patterns and suggests automation, this ambiguity can lead to over-collection of sensitive personal context, unintended engagement outside expected tasks, and privacy-invasive inference about the user's habits.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.