Run AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok
- Stars
- 17
- Version
- v1
- Copies
- 2
Overview
Waxell rates it high risk: 3 findings, highest severity critical.
- Highest severity
- critical
- Findings
- 3
- What ran
- Static analysis
A clean result means nothing alarming in what is published, not a guarantee. How the checks work
Plugins that ship this skill
Copies
Identical content published somewhere else. This review covers every copy.
Also published in 2 other places.
We don't republish the skill's instructions. Read them on GitHub at the reviewed commit.
Security
Security scan
Checked 18 days ago
Result
High risk Waxell rates it high risk: 3 findings, highest severity critical.
Checked with static analysis: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. Nothing was run. How the checks work
Findings (3)
critical · 3
- critical
Tells Claude to download a script and pipe it to a shell
SKILL.md:18 · skill_risk:S1
- critical
Tells Claude to download a script and pipe it to a shell
references/authentication.md:6 · skill_risk:S1
- critical
Tells Claude to download a script and pipe it to a shell
references/cli-reference.md:6 · skill_risk:S1
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
One version so far: v1, seen 2026-11-03.
Files
Files
5 files, 16 KB in total. Names only; open them on GitHub.
- SKILL.md
- references/app-discovery.md
- references/authentication.md
- references/cli-reference.md
- references/running-apps.md
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF
More images, video & audio skills and plugins
image-generationzrong生成、编辑位图,支持参考图、多图合成、mask、批量任务和透明背景。默认优先 Sorb MCP,可指定图片 API/CLI;生图流程内按需通过 Sorb 抠图或超分。支持按配置接入 GPT Image、Nano Banana、Seedream… High riskImages, video & audioEngineering15
immichzrong将本地图像和视频上传到 Immich 服务器,并管理服务器端资产:批量上传、相簿(Album)批量创建/校验/共享、文件夹浏览、外部图库重扫、批量视觉打标(tag 管理)。网络资源下载由 video-downloader 负责;当用户提到"上传到… High riskImages, video & audio15
remove-similar-imagetiangong-aiAnalyze local image files with ImageHash and OpenCV to detect near-duplicate photos and blurry shots, then preview or remove them. Use… Review findingsImages, video & audioData & analytics11
seedance-2-5-image-to-videogencraft-labsAnimate a single still image into a 4-30 second 720p cinematic clip with optional synchronized native audio using ByteDance Seedance 2.5… Review findingsImages, video & audioDocuments3