ClawHub
Back to skill

Security audit

Image Forge

Security checks for vulnerabilities and agentic risk

Overview

ImageForge is a disclosed image-generation skill that uses a fixed third-party image API and local key storage for that purpose.

Before installing, be comfortable giving this skill a NextAI Code API key and allowing prompts and edit source images to be sent to www.nextai-code.com. Avoid using sensitive images or credentials you would not trust with that provider, and note that the setup page and one confirmation phrase are Chinese-localized.

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill instructs the agent to use shell, read and write files, access environment variables, and make network calls, but no permissions are declared. That creates a transparency and policy-enforcement gap: a host relying on declared permissions may allow the skill to operate with broader capabilities than reviewers or users expect.

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The instruction to end with the fixed Chinese phrase “确认后我再生成。” can override the user's language preference and create inconsistent or coercive UX behavior. In a multilingual agent, hardcoded output language requirements are risky because they may cause unintended disclosure, confusion, or failure to follow higher-priority user language/context requirements.

Static analysis

Detected: suspicious.dynamic_code_execution, suspicious.exposed_secret_literal

Dynamic code execution detected.

Critical
Code
suspicious.dynamic_code_execution
Location
scripts/test_image_forge.py:22

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
scripts/test_image_forge.py:197