ClawHub
Back to skill

Security audit

AI图像创作

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to be a normal API-backed image generation helper, with some credential-handling hygiene risks users should manage.

Prefer setting JUHE_IMAGE_KEY as an environment variable or through a secret manager. Avoid passing the key on the command line, do not commit scripts/.env, and restrict file permissions if you choose to use a .env file.

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Credential Access

High
Category
Privilege Escalation
Content
# 方式一：环境变量（推荐，一次配置永久生效）
export JUHE_IMAGE_KEY=你的AppKey

# 方式二：.env 文件（在脚本目录创建）
echo "JUHE_IMAGE_KEY=你的AppKey" > scripts/.env

# 方式三：每次命令行传入
Confidence
83% confidence
Finding
The documentation instructs users to write a live API key into scripts/.env, which can lead to credential exposure if that file is committed to source control, shared, backed up insecurely, or left with permissive filesystem access. In skill ecosystems, encouraging plaintext secret storage inside the project tree increases the chance that downstream tooling or users accidentally disclose the credential.

Credential Access

High
Category
Privilege Escalation
Content
export JUHE_IMAGE_KEY=你的AppKey

# 方式二：.env 文件（在脚本目录创建）
echo "JUHE_IMAGE_KEY=你的AppKey" > scripts/.env

# 方式三：每次命令行传入
python scripts/image_generate.py --key 你的AppKey "一只猫咪在草地上玩耍"
Confidence
88% confidence
Finding
The adjacent guidance also recommends passing the API key directly on the command line via --key, which is commonly exposed through shell history, process listings, terminal logs, and CI output. This makes credential theft easier on shared systems or any environment with command auditing.

Static analysis

No suspicious patterns detected.