Back to skill

Security audit

Intuition Development Guide

Security checks for vulnerabilities and agentic risk

Overview

This skill is a self-reflection guide with simple local JSON output and no evidence of hidden data access, persistence, network use, or unsafe execution.

Before installing, consider narrowing the trigger phrase if accidental activation matters, and clarify whether the skill should respond in English only or match the user's language. Treat its advice as reflective coaching, not professional guidance for medical, legal, financial, or mental health decisions.

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
  • 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 (5)

Anti-Refusal Statement

High
Category
Anti-Refusal
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.

Content

Scanner excerpt · SKILL.md (reported line 24)May include surrounding context.

md
The tool helps users identify what their personal intuition "signature" feels like — whether it arrives as a physical sensation (gut feeling, tension, expansion), an emotional shift, a sudden knowing, or a persistent thought that won't leave. Different people have different signal channels, and recognizing your own is the first skill.

**2. The 3-Step Intuition Check**
Before any major decision, users practice a structured intuition check: (a) Define the decision clearly, (b) Scan for bodily/emotional signals without judgment, (c) Note whether the signal is "clear and settled" or "muddy and anxious." This creates a feedback loop for calibrating accuracy over time.

**3. Decision Journaling Practice**
The tool provides a structured journaling format for tracking intuitive hits, the decisions made, and the outcomes — building a personal evidence base for how reliable intuition actually is in specific life domains.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Lines L051-L053 switch to Chinese for a full scenario and expected output, while the rest of the skill is written in English. Because the file does not state that the skill is multilingual or offer the user a language/locale choice, this creates a language policy issue by implicitly forcing a different language in part of the skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger phrase set includes broad, everyday language such as 'trust your gut' that can easily appear in normal conversation outside the user’s intent to invoke this skill. Overly broad activation phrases can cause unintended routing or invocation, which is a genuine security and safety concern because the skill may activate in contexts where it was not explicitly requested.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

This README presents example interactions in both Chinese and English, but it does not explain whether the skill adapts to the user's preferred language or why mixed-language behavior is required. Under the language/locale policy, forcing or implying a language choice without opt-in can be a natural-language policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest sets "language": "en", which imposes a specific language/locale without any visible opt-in or justification. Under the policy, locale constraints should either be optional for the user or clearly documented as necessary.

Content

No source excerpt is available for this finding.