No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by unclecode · Agent Tool · ★ 119
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is modelprint safe to install? View the security audit →
modelprint One page that answers one question: who is really behind that API? Run infrastructure probes against any OpenAI-compatible endpoint and compare the fingerprints, side by side. Plumbing does not lie; personality does. Try it: unclecode.github.io/modelprint No install, no build, no server. Your API keys stay in your browser tab; every call goes from your browser straight to the provider. Why I built this On 21 August 2026 a stealth model called Ox Alpha appeared on OpenRouter and the whole timeline turned into a detective game. The best evidence was not in anyone's hot take. It was scattered across replies: one person compared token counts, one person read error codes, one person sent temperature 2.0 and let the upstream error speak. Each trick lived and died in a single reply. I collected them into one tool. And the same tricks matter far beyond stealth models: two days earlier I showed that DeepSeek's API silently serves a different model under the old name. Providers move models behind aliases and nothing tells you. This page is how you check.
| Stars | 119 |
| Forks | 14 |
| Language | JavaScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 67.3433811220963/100 |
| Open Issues | 2 |
| Last Updated | 2026-09-19 |
| Created | 2026-08-21 |
| Platforms | browser, node |
| Est. Tokens | ~14k |
These tools work well together with modelprint for enhanced workflows:
Looking for a modelprint alternative? If you're comparing modelprint with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Build mods for Claude Code: Hook any request, modify any response, /model "with-your-custom-model", intelligen
🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support
Run LLM prompts from your shell
Proxy server that converts Anthropic API requests to OpenAI format and sends it to OpenRouter. It's used to us
Examples of integrating the OpenRouter API
An agent framework for Go with graph-aware memory, UTCP-native tools, and multi-agent orchestration. Built for
Explore other popular agent tool tools:
modelprint is Who is really behind that API? Fingerprint any OpenAI-compatible endpoint in the browser: 9 infrastructure probes, side-by-side comparison, community-extensible.. It is categorized as a Agent Tool with 119 GitHub stars.
modelprint is primarily written in JavaScript. It covers topics such as ai-tools, fingerprinting, llm.
You can find installation instructions and usage details in the modelprint GitHub repository at github.com/unclecode/modelprint. The project has 119 stars and 14 forks, indicating an active community.
modelprint is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to modelprint on Agent Skills Hub include ccproxy, web-agent-protocol, runprompt. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: