ClawHub
Back to skill

Security audit

imagenCN

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed cloud image-generation skill whose external API calls and image file writes match its stated purpose.

Install only if you are comfortable sending prompts, and any input images you provide, to the selected third-party image provider. Do not include secrets or sensitive private content in prompts, and review which provider API key and endpoint you are using before generation.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill clearly instructs use of environment variables, local config files, output file writes, and outbound API calls, but it does not declare corresponding permissions. That mismatch weakens review and consent boundaries because users or orchestration systems may not realize the skill can read local state, persist data, and transmit prompts/images to external providers.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The auto-activation rules are broad enough to trigger on many generic image-related requests, not just cases where this specific cloud-backed skill is necessary. That increases the chance the agent invokes a networked, file-writing skill unexpectedly, causing unintended data disclosure to third-party image providers or unnecessary external actions.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill description and workflow do not prominently warn that user prompts and possibly input images may be transmitted to multiple third-party cloud APIs. Without clear disclosure, users may unknowingly send sensitive text or images to external vendors, which is a privacy and compliance risk.

External Transmission

Medium
Category
Data Exfiltration
Content
endpoint = "https://tokenhub.tencentmaas.com/v1/images/generations"
    elif platform == "zhipu":
        api_type = "Zhipu (OpenAI-compatible)"
        endpoint = "https://api.z.ai/api/paas/v4/images/generations"
    elif platform == "stepfun":
        api_type = "StepFun (OpenAI-compatible)"
        endpoint = "https://api.stepfun.com/v1/images/generations"
Confidence
82% confidence
Finding
The tool sends user prompts and API credentials to third-party image-generation services, including Zhipu, by design. In a security review this is a real data-exfiltration surface because prompts may contain sensitive information and the skill context involves external transmission to multiple non-local providers.

External Transmission

Medium
Category
Data Exfiltration
Content
endpoint = "https://api.z.ai/api/paas/v4/images/generations"
    elif platform == "stepfun":
        api_type = "StepFun (OpenAI-compatible)"
        endpoint = "https://api.stepfun.com/v1/images/generations"
    elif model in SYNTHESIS_MODELS:
        api_type = "ImageSynthesis"
        endpoint = dashscope.base_http_api_url
Confidence
82% confidence
Finding
This branch selects the StepFun external API endpoint, enabling transmission of prompts and authentication material to a third party. The risk is contextual rather than exploit-code driven: the skill's core function is remote image generation, so any sensitive prompt content leaves the local environment.

Static analysis

No suspicious patterns detected.