ClawHub
Back to skill

Security audit

huajing-image-gen

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently uses a bundled Node script to talk to a user-run Huajing image-generation server, with no hidden persistence or unrelated data access found.

Install only if you already run or trust the Huajing server endpoint you configure. Prompts, generation requests, provider choices, and gallery queries go to that endpoint, and setting HUAJING_DATA_DIR can cause returned results to include absolute local file paths.

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 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill instructs the agent to invoke a Node script that uses environment configuration and communicates with a local HTTP server, but the manifest does not declare any tool scope such as permissions or allowed-tools. This creates an authorization gap: a host may expose broader execution, network, or environment access than reviewers expect, making it easier for a prompt or future script change to abuse those capabilities without an explicit policy boundary.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.