ClawHub
Back to skill

Security audit

Image Generation

Security checks for vulnerabilities and agentic risk

Overview

This skill gives normal image-generation workflow guidance and includes a read-only checker for generated image files.

Install this if you want agents to follow a consistent image-generation and artifact-validation workflow. Expect it to create or update image files and downstream documents when asked, and to optionally run a local read-only checker over the chosen repository root.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The description suggests a content-generation or editing skill that can create/revise documents and images. The code does not generate, revise, or review content; it only validates the presence and freshness of generated image artifacts associated with *.image.genai prompt files. Its actual purpose is a repository/workspace consistency check for image outputs, which is materially different from the declared purpose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.