Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/meitu/meitu-skillsnpx agentmods add skills/meitu/meitu-skills/image-cutoutWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/meitu/meitu-skills/image-cutout)<a href="https://agentmods.dev/skills/meitu/meitu-skills/image-cutout"><img src="https://agentmods.dev/badge/skills/meitu/meitu-skills/image-cutout/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/meitu/meitu-skills/image-cutout"><img src="https://agentmods.dev/badge/skills/meitu/meitu-skills/image-cutout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 5 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 7 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 13 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 15 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 21 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Rogue Agent · line 26 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.02259 |
| Opus 5 | $0.00036 | $0.01130 |
| Sonnet 5 | $0.00014 | $0.00452 |
| Haiku 4.5 | $0.00007 | $0.00226 |
Grade A, and why
image-cutout scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
图片抠图（image-cutout）
Overview
对已有图片做前景主体与背景的精准分离。仅人物、宠物、商品、图标、印章五类主体可调用 SOD，并输出透明底 PNG；非五类主体和白底隔离不调用替代 API。
DAG / API Mapping
- DAG 路由定位：这是
dag_existing_tool_routes中的现有 Meitu 工具路由，不是新建的dag_native命令；参数与执行契约以tools[].cli为准。 - CLI 入口：
meitu image-cutout；image_url必填，model_type可选。 - MCP 入口：
image_cutout，api_path=/v1/hydra_async，api_task_type=mtlab。 - MCP 对外参数：
image_url必填；model_type可选（0=人像、1=商品、2=图形），不传由模型自动判断。 - MCP 内部固定请求：
request_payload.parameter.api_path=/v1/sod_2c_async、function_path=image-cutout、use_fe_rgba=true。use_fe_rgba不是用户参数，不得暴露为 CLI 选项或要求用户提供。 - CLI 与 MCP 的用户参数保持一致；
prompt、target_subject、exclude_subjects均不是对外参数。
Dependencies
- meitu-cli:
>=2.0.6（npm install -g meitu-cli@latest） - 凭证：CONFIG AKSK →
meitu tools update；EXEC AKSK → 实际执行（见根CONFIG.md） - 环境变量：
MEITU_OPENAPI_TOOL_TASK_MODE=command
路径别名：
$VISUAL={OPENCLAW_HOME}/workspace/visual/
Core Workflow
Preflight → Execute → Deliver
Preflight
meitu --version≥ 2.0.6（否则npm install -g meitu-cli@latest）- 确认已跑过
meitu tools update（用 CONFIG AKSK） - 当前 AKSK = EXEC，且
MEITU_OPENAPI_TOOL_TASK_MODE=command - 解析 output_dir：openclaw.yaml →
./output/｜else →$VISUAL/output/image-cutout/；mkdir -p
Execute
触发信号 / 路由规则
核心判断维度：Agent 画面识别的主体类型。
| 场景 | 判定关键词 | 路由 | 输出 |
|---|---|---|---|
| 标准五类主体 | 人物/宠物/商品/图标/印章 | 透明底抠图路径 | 透明底 PNG |
| 非标准主体 | 建筑/植物/车辆/食物/家具/其他 | 返回 UNSUPPORTED_SUBJECT_CATEGORY |
不调用 |
| 用户明确要求白底 | 白底、纯白背景 | 返回 UNSUPPORTED_SUBJECT_CATEGORY |
不调用 |
| 主体类型无法判断 | 无法确认是否属于五类 | 先向用户确认 | 不调用 |
决策顺序：
- Agent 先识别图片主体是否属于支持的五类
- 属于五类 → 通过 CLI 调用
meitu image-cutout；否则返回不支持 - 用户明确指定模型时校验
model_type为0、1或2；未指定时省略该参数，由模型自动选型
CLI 参数
| 参数 | 类型 | 必填 | 默认值 | 说明 |
|---|---|---|---|---|
image_url |
STRING | 是 | -- | 图片地址。缺失 → 提示"请提供需要抠图的图片" |
model_type |
INTEGER | 否 | 自动判断 | 0 人像、1 商品、2 图形；仅允许这三个值 |
MCP 对外参数
| 参数 | 类型 | 必填 | 默认值 | 说明 |
|---|---|---|---|---|
image_url |
STRING | 是 | -- | 单张待处理图片 |
model_type |
INTEGER | 否 | 自动判断 | 0 人像、1 商品、2 图形 |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 177 lines · 72 tokens per session scan A a898c3af1c44
image-cutout is a skill published in the GitHub repository meitu/meitu-skills (32 stars, last pushed 14d ago), licensed MIT. It adds 72 tokens to every session and 2,259 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.