ClawHub
Back to skill

Security audit

emoji-finder

Security checks for vulnerabilities and agentic risk

Overview

This is a simple emoji lookup reference skill with no code execution, network access, persistence, or sensitive data handling.

This skill appears safe to install. The main caveat is that its broad triggers such as "icon" or a standalone emoji may make it appear in conversations where emoji lookup was not intended.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list includes generic terms and a standalone emoji that can activate the skill during ordinary conversation rather than only when a user explicitly wants emoji lookup. This can cause unintended routing or invocation of the skill, reducing reliability and creating opportunities for prompt/skill confusion in larger agent systems.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
82% confidence
Finding

The trigger '表情' is short and broad, so it may match many benign requests that mention expressions, emoticons, or related concepts without intending to invoke this skill. In an agent framework, this increases accidental activation and misrouting risk rather than direct code-execution risk.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
95% confidence
Finding

A single emoji trigger like '😊' is extremely broad because it can appear in normal user messages with no intent to use this skill. This makes accidental invocation highly likely and can interfere with correct tool selection in multi-skill environments.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.