ClawHub
Back to skill

Security audit

image

Security checks for vulnerabilities and agentic risk

Overview

This skill is a marketing-image guidance package with no executable code, persistence, hidden behavior, or credential collection instructions.

Installers should treat this as benign guidance for marketing image production. Do not paste API keys or other secrets into chat; configure provider credentials through the normal secure environment or account settings when a tool actually needs them.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
93% confidence
Finding

The manifest description says to use the skill whenever the user wants to "create, generate, edit, or optimize images" and includes broad phrases like "generate an image" and "create a graphic." These phrases are common in everyday requests and the description does not provide exclusion conditions beyond a few related-skill redirects, which risks unintended invocation for non-marketing or non-specialized image tasks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The markdown instructs the agent to gather whether the user has API keys for image tools, but it does not warn users not to paste secrets directly or explain safe handling expectations. Because API keys are sensitive credentials, the skill description should include a brief user-facing caution when requesting this kind of information.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.