ClawHub
Back to skill

Security audit

Ieum Kit (이음 키트)

Security checks for vulnerabilities and agentic risk

Overview

This skill openly preserves your communication preferences and relationship notes across sessions, with approval required for the initial memory draft.

Review the SOUL.md draft and nightly automation before enabling them. Corrections accumulate automatically, and personal notes survive session resets; periodically review them and remove the automation if you stop using the skill.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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)

Persistent Context Injection

Medium
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.

Content

Scanner excerpt · README.md (reported line 15)May include surrounding context.

md
| Part | Where | What it does |
|---|---|---|
| On waking | top of `SOUL.md` | The agent reads the relationship first, uses the agreed tone in its first reply, and asks about the user before work. |
| Corrections | `SOUL.md` | Each time the user corrects the agent's tone or behavior, the agent adds a permanent rule. The list is append-only. |
| Letter from yesterday's me | `SOUL.md` | A nightly 3–5 line letter about the user's day, mood, and promises. The agent writes it for its next self. |
| First-install interview | `references/interview.md` | The agent asks the user what relationship they want, then drafts `SOUL.md` from the answers. |

Persistent Context Injection

Medium
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: ieum-kit
description: "Use when setting up or keeping an agent's relationship with its user across memory/session resets — first-time 'what kind of relationship do you want' interview, logging a user's correction of the agent's tone or behavior as a lasting rule, or writing the nightly 'letter from yesterday's me'. 이음 키트 - 기억이 끊겨도 관계로 돌아오게 하는 SOUL.md 구조."
license: MIT
---

Static analysis

No suspicious patterns detected.