ClawHub
Back to skill

Security audit

GlowSkin Promo

Security checks for vulnerabilities and agentic risk

Overview

This is a simple skincare affiliate marketing prompt skill with no code execution, persistence, credential access, or hidden system behavior.

Before installing, treat it as a copywriting helper only. Review generated affiliate claims for accuracy, disclosure, platform rules, and skincare advertising requirements, especially around efficacy or dermatologist-style claims.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The example triggers are very broad and can cause the skill to activate on generic marketing requests without clear scoping to skincare affiliate content. This increases the chance of unintended invocation, overlap with unrelated tasks, and misuse for generating potentially deceptive promotional content outside the intended domain.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.