ClawHub
Back to skill

Security audit

AI Product Visual Prompt Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill only helps write structured prompts for product visuals and does not request files, secrets, commands, or persistent access.

This looks safe to install for help drafting AI image and video prompts. Review generated prompts for brand, label, and claim accuracy before using them commercially, and treat the optional external testing site as a separate third-party service.

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
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description is broad enough to match many common creative-image requests, which can cause unintended activation over more appropriate skills. In an agent environment, this increases the chance of prompt-routing errors, leading the skill to influence conversations outside its intended scope and potentially override safer or more specialized handling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The instruction says to produce the final answer in the requested language but then to default to English prompts if the user plans to paste them into image or video models. This imposes a language preference without requiring explicit user choice, which can conflict with locale or language preference policies.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.