ClawHub
Back to skill

Security audit

Socialite Guide

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only photo prompt guide with no code execution, persistence, credential access, or hidden data handling.

Installers should expect a style-specific prompt-writing guide for socialite/luxury AI photos. It may be invoked for some broader glamour or fashion photo requests, so users who do not want that aesthetic should ask the agent for a different style explicitly.

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
Confidence
91% confidence
Finding
The activation conditions are broad enough to match many generic glamour or photo-style requests, not just the narrowly intended 'socialite' use case. Overbroad routing can cause the agent to invoke this skill inappropriately, leading to irrelevant guidance, prompt contamination across domains, and reduced control over which specialized instructions are applied.

Natural-Language Policy Violations

Medium
Confidence
89% confidence
Finding
Throughout the markdown, the skill repeatedly instructs users to use English prompt keywords and examples, such as the '英文描述词' columns and full English prompt templates. Under the stated policy, forcing a specific language without user opt-in or a documented justification is a natural-language policy violation.

Natural-Language Policy Violations

Low
Confidence
83% confidence
Finding
SQP-3 applies to all file types and includes language or locale policy violations. This file is fully written in Chinese and does not provide an opt-in, alternative language, or justification for restricting the guidance to a Chinese-language audience.