ClawHub
Back to skill

Security audit

Image Scene Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed product-image prompt generator with only an optional local batch script for user-supplied JSON files.

Install if you want help writing AI image-generation prompts for product photography. Use the optional batch script only with product JSON files you intend to process, and choose output paths deliberately because it will write the markdown file you specify.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill references a local script and input/output file operations but does not declare any tool scope, permissions, or allowed-tools boundary. In an agent framework, this can lead to unintended file read/write capability exposure or ambiguous authorization, increasing the chance that the skill is invoked with broader filesystem access than intended.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger description is very broad, covering many generic product-photo and image-improvement requests, which can cause the skill to activate in situations where a more appropriate or safer skill should handle the request. Over-broad routing increases the risk of prompt injection surface area and unintended behavior because the skill may process inputs it was not designed to handle reliably.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The activation example "make this look premium" is too vague and can match a wide range of unrelated user requests, causing unreliable skill routing. This ambiguity can lead to inappropriate invocation, context confusion, and accidental handling of tasks outside the skill’s intended scope.

Static analysis

No suspicious patterns detected.