ClawHub
Back to skill

Security audit

Product Desc Writer

Security checks for vulnerabilities and agentic risk

Overview

This is a simple product-copy writing skill with visible promotional payment links, but no code, persistence, credential access, or hidden high-impact behavior.

Review the visible PayPal/USDT upgrade solicitation before installing. Functionally, this skill appears limited to product-copy guidance, but the promotional text is awkwardly embedded and may make the skill feel less polished.

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
95% confidence
Finding

The invocation examples are overly broad and include malformed promotional content mixed into a usage example, which can cause an agent to trigger this skill in loosely related contexts rather than only for product-description tasks. Overbroad activation increases prompt-surface exposure and can route unrelated user input into a skill containing monetization links and payment instructions, which is unsafe and unnecessary for normal operation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.