Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Jimeng-Image-Generater

v0.1.0

Use Jimeng AI 4.0 (Volcengine) to generate images from text or image references, and optionally send results to Feishu.

1· 791·4 current·4 all-time
bytangzhan_aicoding@tangc

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for tangc/jimeng-t2i-i2i-image-generator.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Jimeng-Image-Generater" (tangc/jimeng-t2i-i2i-image-generator) from ClawHub.
Skill page: https://clawhub.ai/tangc/jimeng-t2i-i2i-image-generator
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Canonical install target

openclaw skills install tangc/jimeng-t2i-i2i-image-generator

ClawHub CLI

Package manager switcher

npx clawhub@latest install jimeng-t2i-i2i-image-generator
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
The name/description (Jimeng/Volcengine image generation, optional Feishu delivery) aligns with the scripts: they call visual.volcengineapi.com and perform t2i/i2i tasks. However the registry metadata lists no required environment variables or primary credential while both SKILL.md and scripts require VOLCENGINE_AK and VOLCENGINE_SK — a clear mismatch between claimed metadata and actual requirements.
!
Instruction Scope
SKILL.md instructs running the included scripts which: (1) use VOLCENGINE_AK and VOLCENGINE_SK to sign API requests to visual.volcengineapi.com; (2) submit and poll jobs and print full JSON responses; (3) when a target is supplied, POST a JSON payload to http://localhost:18789/message containing target, message text, and the image URL. The use of a localhost endpoint is not documented in the metadata and could forward generated URLs or metadata to any local listener — an unexpected externalization path. The instructions do not read other system files, but they do rely on env vars that are not declared in registry metadata.
Install Mechanism
No install spec; skill is instruction + scripts only. No remote downloads, no archive extraction, and included Python/Bash scripts are present. This is low install risk.
!
Credentials
The scripts legitimately need VOLCENGINE_AK and VOLCENGINE_SK to call Volcengine APIs — that is proportionate to the stated purpose. But the registry metadata did not declare these required env vars or a primary credential, which is an incoherence and security/usability concern. Additionally, the script assumes a local Feishu bridge (localhost:18789) instead of requiring Feishu credentials; this delegates Feishu auth to a local service whose presence and behavior are unknown.
Persistence & Privilege
always:false and no install-time modifications are requested. The skill does not alter other skills or system settings; it only executes included scripts when invoked. No elevated persistence or privileges are requested.
What to consider before installing
This skill appears to be a legitimate wrapper for Volcengine (Jimeng) image generation, but there are two issues you should consider before installing or running it: (1) the scripts require VOLCENGINE_AK and VOLCENGINE_SK (secret credentials) even though the registry metadata did not declare them — verify you trust the skill source before providing keys and prefer an account/key with limited scope and short lifetime; (2) when asked to deliver results to Feishu the script posts a JSON payload to http://localhost:18789/message (a local listener), not directly to Feishu's official API. If you don't already run a trusted local bridge that forwards to Feishu, that localhost endpoint could capture or forward generated image URLs and captions unexpectedly. Recommendations: inspect the scripts (you already have them), confirm the skill author/source, run the skill in an isolated environment (or container) if you must supply real credentials, consider creating an ephemeral/limited Volcengine key, and verify or replace the localhost callback with a delivery mechanism you control. Additional information that would raise confidence: a known homepage or repository, registry metadata corrected to declare required env vars, and an explanation of the expected local Feishu bridge or an option to post directly to Feishu with explicit credentials.

Like a lobster shell, security has layers — review code before you run it.

latestvk970t3ynp3h3d8mz84tc77sa11828qy3
791downloads
1stars
1versions
Updated 17h ago
v0.1.0
MIT-0

Jimeng AI 4.0 图片生成 Skill

使用火山引擎即梦AI 4.0 生成图片。

环境变量

export VOLCENGINE_AK="你的AccessKeyID"
export VOLCENGINE_SK="你的SecretAccessKey"

使用方式

./jimeng.sh <mode> <prompt> [reference_url] [target] [options]

参数说明

参数必填说明
modet2i (文生图) 或 i2i (图生图)
prompt图片描述
reference_url图生图时可选参考图片URL,不填则使用默认图片
target可选飞书用户ID,如 user:ou_xxx,不填则只输出URL
options可选额外选项,如 force_single=true

示例

文生图 (t2i)

# 文生图 - 生成一只可爱的猫咪
./jimeng.sh t2i "一只可爱的猫咪"

# 文生图 - 发送给飞书用户
./jimeng.sh t2i "蓝天白云" "user:ou_5ab7e4d11d7f28bebff34796cc967e24"

# 文生图 + 参考风格图
./jimeng.sh t2i "变成油画风格" "https://example.com/style.jpg"

图生图 (i2i)

# 图生图 - 使用默认参考图(Clawra头像)
./jimeng.sh i2i "戴上墨镜"

# 图生图 - 使用默认参考图
./jimeng.sh i2i "变成卡通风格"

# 图生图 - 自定义参考图
./jimeng.sh i2i "把这张照片变成素描风格" "https://example.com/photo.jpg"

# 图生图 - 发送给飞书用户
./jimeng.sh i2i "戴上牛仔帽" "" "user:ou_xxx"

默认参考图

图生图模式默认使用 Clawra 头像作为参考:

https://cdn.jsdelivr.net/gh/SumeLabs/clawra@main/assets/clawra.png

输出说明

  • 直接运行:输出图片URL
  • 指定 target:自动发送到飞书

图片格式

  • 即梦AI 默认输出 PNG 格式
  • URL 后缀是 .image,飞书可以正常发送
  • 用户保存:复制链接后把 .image 改成 .png

文件结构

jimeng/
├── SKILL.md      # 本文件
└── scripts/
    ├── sign.py   # 火山引擎签名
    └── jimeng.sh # 主脚本

Comments

Loading comments...