← 返回 Skills 市场

AIML Generate images and videos

Name: AIML Generate images and videos
Author: aimlapihello

作者 AI/ML API · GitHub ↗ · v1.0.2

cross-platform ⚠ suspicious

1513

总下载

当前安装

版本数

在 OpenClaw 中安装

/install aiml-image-video

功能描述

Generate images or videos via AIMLAPI from prompts. Use when Codex needs reliable AI/ML API media generation with retries, explicit User-Agent headers, and a...

使用说明 (SKILL.md)

AIMLAPI Media Generation

Overview

Generate images and videos via AIMLAPI with scripts that include retries, API key file fallback, verbose logs, and required User-Agent headers on every request.

Quick start

export AIMLAPI_API_KEY="sk-aimlapi-..."
python3 {baseDir}/scripts/gen_image.py --prompt "ultra-detailed studio photo of a lobster astronaut"
python3 {baseDir}/scripts/gen_video.py --prompt "slow drone shot of a foggy forest"

Tasks

Generate images

Use scripts/gen_image.py with /v1/images/generations.

python3 {baseDir}/scripts/gen_image.py \
  --prompt "cozy cabin in a snowy forest" \
  --model aimlapi/openai/gpt-image-1 \
  --size 1024x1024 \
  --count 2 \
  --retry-max 4 \
  --user-agent "openclaw-custom/1.0" \
  --out-dir ./out/images

Generate videos (async AIMLAPI flow)

Use scripts/gen_video.py with the real async flow:

POST /v2/video/generations (create task)
GET /v2/video/generations?generation_id=... (poll status)
download video.url when status is completed

python3 {baseDir}/scripts/gen_video.py \
  --model google/veo-3.1-t2v-fast \
  --prompt "time-lapse of clouds over a mountain range" \
  --poll-interval 10 \
  --max-wait 1000 \
  --user-agent "openclaw-custom/1.0" \
  --out-dir ./out/videos

References

references/aimlapi-media.md: endpoint notes, async polling statuses, and troubleshooting.
README.md: changelog-style summary of new instructions.

安全使用建议

This skill appears to do what it says: it requires AIMLAPI_API_KEY and will POST prompts to api.aimlapi.com and download returned media URLs. Before installing, verify the AIMLAPI service and that you trust the skill source (homepage unknown). Protect the API key (use a scoped key if possible, and secure any --apikey-file). Be aware that downloaded media URLs come from the remote API — validate or sandbox usage if you worry about malicious payloads or unexpected content. Finally, avoid including sensitive data in prompts sent to the remote API.

功能分析

Type: OpenClaw Skill Name: aiml-image-video Version: 1.0.2 The skill is classified as suspicious due to a critical Local File Read (LFR) vulnerability in `scripts/gen_image.py`. The `--image-url` argument can be used to read arbitrary local files (e.g., `/etc/passwd`, `~/.ssh/id_rsa`), base64 encode their content, and send them to the `api.aimlapi.com` endpoint as part of the image generation payload. While the destination is a legitimate API, this constitutes an information disclosure risk. Additionally, both `scripts/gen_image.py` and `scripts/gen_video.py` allow reading arbitrary files via the `--apikey-file` argument, although this risk is acknowledged in `README.md`.

能力评估

✓ Purpose & Capability

Name/description, declared env var (AIMLAPI_API_KEY), example endpoints (/v1 images, /v2 video), and included scripts all align with a media-generation helper for AIMLAPI.

✓ Instruction Scope

SKILL.md only instructs exporting AIMLAPI_API_KEY and running the provided scripts. The scripts perform expected actions: build payloads, POST to AIMLAPI, poll the async video endpoint, and download returned media. They do not read unrelated system files or request unrelated credentials.

✓ Install Mechanism

No install spec (instruction-only) and bundled scripts only; nothing is downloaded during install and no external installers or archive extraction are used.

✓ Credentials

Only AIMLAPI_API_KEY is required (with optional --apikey-file). That matches the skill's purpose. No unrelated secrets or config paths are requested.

✓ Persistence & Privilege

Skill is not always-enabled, does not request elevated/system-wide persistence, and does not modify other skills or agent configs.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install aiml-image-video
安装完成后，直接呼叫该 Skill 的名称或使用 /aiml-image-video 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.2

- No file or documentation changes detected in this version. - Functionality and instructions remain unchanged from the previous release.

v1.0.1

- Added IMAGE-TO-IMAGE.md and IMAGE-TO-VIDEO.md references for additional documentation. - Removed the obsolete _meta.json file. - No changes to usage instructions or core functionality.

v1.0.0

Initial release of aimlapi-media-gen - Generate images or videos via AIMLAPI using user prompts. - Supports retries, fallback to API key file, explicit User-Agent headers, and verbose logging. - Async video generation with polling and download upon completion. - Includes scripts: `gen_image.py` for images and `gen_video.py` for videos. - Detailed usage and task examples provided in SKILL.md.

元数据

Slug aiml-image-video

版本 1.0.2

许可证 —

累计安装 6

当前安装数 4

历史版本数 3

常见问题