Skill flagged — suspicious patterns detected

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

cli-anything-gimp

v1.0.0

GIMP 图像编辑 via CLI-Anything. 用于处理图片编辑任务,如创建项目、添加图层、调整图像、导出等。当用户需要用 GIMP 处理图片时使用此技能。

0· 272·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for sly27/cli-anything-gimp.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "cli-anything-gimp" (sly27/cli-anything-gimp) from ClawHub.
Skill page: https://clawhub.ai/sly27/cli-anything-gimp
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 sly27/cli-anything-gimp

ClawHub CLI

Package manager switcher

npx clawhub@latest install cli-anything-gimp
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
Name/description claim a CLI wrapper for GIMP and the SKILL.md documents commands that match that purpose. However the skill does not declare the required binary 'cli-anything-gimp' or an install source; instead it assumes a local repo at ~/.openclaw/workspace/CLI-Anything/gimp/agent-harness. That implicit dependency is unexpected for an instruction-only skill.
!
Instruction Scope
The instructions tell the agent to activate a virtualenv and run pip install (including pip install -e . in a local path). That can execute arbitrary local code and modifies the runtime environment. The SKILL.md also hardcodes paths under ~/.openclaw, assuming files exist there, which grants the skill broad discretion to run code from the user's workspace.
!
Install Mechanism
There is no formal install spec in the registry. Instead, the runtime instructions instruct direct pip installs (click, numpy, Pillow, prompt-toolkit) and a local editable install (pip install -e .) from a repo path. Installing/editing local packages via pip can run arbitrary setup/build scripts; without a trustworthy source (PyPI/GitHub release) this is risky.
Credentials
The skill does not request environment variables, credentials, or config paths beyond using a path under the agent workspace (~/.openclaw). No secrets or unrelated service tokens are requested.
Persistence & Privilege
always is false and there are no indications the skill attempts to persistently modify other skills or system-wide agent settings. It does instruct creating/using a venv under ~/.openclaw, which is limited to the agent workspace.
What to consider before installing
This skill appears to be a CLI wrapper for GIMP, but its SKILL.md tells you to pip-install code from a local workspace path (~/.openclaw/workspace/CLI-Anything/...). Before installing or running: (1) verify the contents and origin of ~/.openclaw/workspace/CLI-Anything/gimp/agent-harness — don't run pip install -e . on unknown code, (2) prefer a published package (PyPI or an official GitHub release) or request the author to provide a safe install spec, (3) run installs in an isolated environment (container or throwaway VM) if you must test, (4) ensure GIMP is the intended target and that no unexpected network or filesystem access occurs. If the publisher/source can be provided (homepage, repo, signed release), the assessment could be upgraded to benign.

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

clivk977x98rqhbxx50fpqp28s63h182zanhgimpvk977x98rqhbxx50fpqp28s63h182zanhgraphicsvk977x98rqhbxx50fpqp28s63h182zanhimage-editingvk977x98rqhbxx50fpqp28s63h182zanhlatestvk977x98rqhbxx50fpqp28s63h182zanh
272downloads
0stars
1versions
Updated 16h ago
v1.0.0
MIT-0

GIMP CLI-Anything Skill

基于 CLI-Anything 生成的 GIMP 命令行工具,让 AI Agent 可以控制 GIMP 进行图像编辑。

虚拟环境

此 skill 使用独立虚拟环境:

  • 路径: ~/.openclaw/workspace/cli-anything-venv/bin/
  • 命令: ~/.openclaw/workspace/cli-anything-venv/bin/cli-anything-gimp

前置条件

确保虚拟环境已激活且 GIMP CLI 已安装。如遇问题,尝试重新安装:

# 激活虚拟环境并安装
source ~/.openclaw/workspace/cli-anything-venv/bin/activate
pip install click numpy Pillow prompt-toolkit
cd ~/.openclaw/workspace/CLI-Anything/gimp/agent-harness
pip install -e .

核心命令

# 获取帮助
cli-anything-gimp --help

# 进入交互模式 (REPL)
cli-anything-gimp

# 项目管理
cli-anything-gimp project new --width 1920 --height 1080 -o poster.json
cli-anything-gimp project open poster.json

# 图层操作
cli-anything-gimp layer add -n "Background" --type solid --color "#1a1a2e"
cli-anything-gimp layer list
cli-anything-gimp layer remove "Layer 1"

# 画布操作
cli-anything-gimp canvas resize --width 1024 --height 768

# 导出
cli-anything-gimp export png -o output.png
cli-anything-gimp export jpg -q 90 -o output.jpg

# 滤镜
cli-anything-gimp filter blur --radius 5
cli-anything-gimp filter sharpen
cli-anything-gimp filter gaussian-blur --radius 2.5

# 绘画操作
cli-anything-gimp draw brush -n "Circle (19)" --size 10 --color "#FF0000"
cli-anything-gimp draw erase --size 20

常用工作流

1. 创建新图像

cli-anything-gimp project new --width 800 --height 600 -o my_image.json
cli-anything-gimp layer add -n "Background" --type solid --color "#FFFFFF"
cli-anything-gimp layer add -n "Text Layer" --type text --text "Hello"
cli-anything-gimp export png -o my_image.png

2. 编辑现有图像

cli-anything-gimp media open input.jpg
cli-anything-gimp filter blur --radius 3
cli-anything-gimp layer add -n "Watermark" --type text --text "©2026"
cli-anything-gimp export png -o output.png

3. 批量处理

# 在 REPL 模式下可以连续执行多条命令
cli-anything-gimp repl < commands.txt

输出格式

# JSON 格式输出 (便于程序解析)
cli-anything-gimp --json layer list

# 人类可读格式 (默认)
cli-anything-gimp layer list

注意事项

  1. GIMP 必须在系统上已安装才能进行实际图像处理
  2. 某些高级功能可能需要 GIMP Python 插件
  3. 复杂操作建议在 REPL 交互模式下完成

故障排除

  • 命令找不到: 检查虚拟环境路径是否正确
  • 模块缺失: pip install numpy Pillow prompt-toolkit
  • GIMP 未安装: 使用 Homebrew 安装 brew install gimp

Comments

Loading comments...