ClawHub
Back to skill

Security audit

Emoji

Security checks for vulnerabilities and agentic risk

Overview

This is a simple emoji reference skill with broad trigger wording but no code, network access, persistence, credential use, or hidden harmful instructions.

Installers should know this skill may be invoked during general reply composition because its trigger wording is broad. Its inspected contents are limited to emoji suggestions, so the main practical consideration is whether that broad activation is desirable in your workflow.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

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

md
---
name: emoji
description: Pick the right emoji or sticker for any message context. Triggers when composing replies, reacting to messages, adding emoji to text, or when asked for emoji/sticker suggestions. Provides ~1000 emojis organized by scenario so agents can quickly find the perfect emoji for any mood, topic, or platform.
---

# Emoji Picker

When replying to messages, reacting, or adding visual flavor to text, read [references/emoji-catalog.md](references/emoji-catalog.md) to find the right emoji.

## How to Use

1. Identify the **tone/mood** of the message you're composing (celebration, sympathy, hum

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · references/emoji-catalog.md (reported line 65)May include surrounding context.

md
## 15. Animals & Pets 动物与宠物

🐶 🐱 🐭 🐹 🐰 🦊 🐻 🐼 🐻‍❄️ 🐨 🐯 🦁 🐮 🐷 🐽 🐸 🐵 🙈 🙉 🙊 🐒 🐔 🐧 🐦 🐤 🐣 🐥 🦆 🦅 🦉 🦇 🐺 🐗 🐴 🦄 🐝 🪱 🐛 🦋 🐌 🐞 🐜 🪰 🪲 🪳 🦟 🦗 🕷️ 🕸️ 🦂 🐢 🐍 🦎 🦖 🦕 🐙 🦑 🦐 🦞 🦀 🪸 🐡 🐠 🐟 🐬 🐳 🐋 🦈 🐊 🐅 🐆 🦓 🦍 🦧 🐘 🦛 🦏 🐪 🐫 🦒 🦘 🐃 🐂 🐄 🐎 🐖 🐏 🐑 🦙 🐐 🦌 🐕 🐩 🦮 🐕‍🦺 🐈 🐈‍⬛ 🪶 🐓 🦃 🦚 🦜 🦢 🦩 🕊️ 🐇 🦝 🦨 🦡 🦫 🦦 🦥 🐁 🐀 🐿️ 🦔 🐾 🐉 🐲

## 16. Music & Entertainment 音乐与娱乐

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill manifest advertises triggers like "any message context," "composing replies," and "reacting to messages," which are so broad that the skill could activate across ordinary messaging workflows far beyond a narrow emoji-assistance use case. Over-broad activation increases the chance of unnecessary context access and makes the skill easier to invoke in unrelated conversations, expanding its attack surface even if the content itself is harmless.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The section titled "Chinese / CJK Context 中文语境" explicitly introduces locale-specific content, and many headings throughout the file are bilingual with Chinese text. Because the file does not indicate that Chinese/CJK output is optional or user-selected, it can be read as imposing a specific language/locale context without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.