A zero-dependency auditor for AI agent exposure (secrets, SSH, configs)

A free, MIT-licensed Node.js tool called Dante (published on npm as dante-watch) audits a machine for secrets, SSH keys and risky configuration that an AI coding agent running with the user's own rights could reach, arguing that signature antivirus cannot catch a threat that is legitimate software rather than malware. The tool has zero dependencies and no install scripts, makes no network calls on its own, and reaches the internet only through curl after the user approves a displayed command; it is invoked with `npx dante-watch` and reports each verdict with a proof line. An optional bait-watch feature plants honeypot credentials and alerts the user by email within seconds if one is used, priced at 1.99 EUR a month after a free first month, while the watchman itself is free.

Antivirus for AI agents: what actually protects your machine An AI coding agent runs with your rights. It can read your .env , your SSH keys and your shell history, and run commands. Nothing "malicious" has to be installed for that to go wrong. This page explains why signature antivirus does not cover that, what does, and how to check your own machine in three minutes. DO NOT TRUST US. CHECK IT IN ONE MINUTE. - Runs on your machine, offline. The watchman needs no internet and no account to check. Once it is installed, turn Wi-Fi off and run it: it still works. He makes no network call on his own . Only three things can reach out fetch a knowledge pack, look at the shop catalog, the optional bait watch , and each one only after you say yes to the exact command he shows first. - Nothing hidden in the package. No dependencies, no install scripts. Nothing runs when you install it. - Open and readable. MIT-licensed, plain JavaScript. You can download exactly what npm serves and read the whole program. - The only way out is curl, and you can count it. Dante has no web code of his own no HTTP library ; to reach the internet he starts curl , and the check below lists every place where that can happen. The only direct connection he opens himself is the question "does port 22 answer?" on a server you named. - Extendable from outside, safely. New knowledge arrives as signed data packs rules, never code , checked against a key built into the program. A downloaded pack installs with pack <file , without any network. The one-minute check terminal, Node.js installed . Copy each line, press Enter: npm view dante-watch dependencies scripts dependencies = {} and no scripts. npm pack dante-watch && tar -xzf dante-watch- .tgz package/src : read it. grep -rn 'execProgram. "curl"' package/src what touches the network https://ai-agent-antivirus.space/docs/ network . TL;DR - What: Dante is a free watchman for your own computer and servers. It finds the things an AI agent or a thief would grab first: loose keys, open doors, risky settings. - Why not antivirus: an agent is legitimate software with your rights. There is no virus to catch. There is reach to limit. - How: npx dante-watch , then say "check my computer". It only reads, and every verdict shows its proof line. - Where: Mac, Windows, Linux, and servers you reach by SSH. Nothing leaves your machine unless you say yes to a command he shows first. - Bait watch: Dante lays honeypots, fake keys that look exactly like what a thief or a rogue agent grabs first. If someone uses one, it calls us and you get a mail within seconds. First month free, then 1.99 EUR a month; that money pays for the research behind it. We are building this out. - Cost: the watchman itself is free. Optional knowledge packs and the bait watch if you want more. Why a normal antivirus is the wrong tool for this A classic antivirus compares files and behaviour against known malware. That works when something foreign runs on the machine. With an AI agent the situation is different: the program is legitimate, it is signed, it was installed on purpose, and it acts with your user rights. The risk is not a virus. The risk is what the agent can reach and what can talk it into using it. That is the reasoning behind the product, not a measured detection statistic: if the dangerous thing is a secret lying in a readable file, the useful check is "which secrets lie where, and who can read them", not "does this binary match a signature". This is not theory. In August 2025 the s1ngularity attack https://www.okta.com/en-ca/blog/threat-intelligence/the-s1ngularity-attack--when-attackers-prompt-your-ai-agents-to/ on the Nx build tool shipped malware that looked for installed AI command-line assistants and told them to search the victim's file system for credentials, SSH keys and wallets. Weeks later the self-spreading Shai-Hulud npm worm https://cloudsmith.com/blog/npm-ecosystem-update-s1ngularity-and-shai-hulud-attacks hunted for publishing tokens. Both worked because the secrets were sitting where any process of the user could read them. What Dante is Dante is a free, open command-line watchman for machines you own: your Mac, Linux or Windows computer, and servers you can reach by SSH. You talk to it in plain German, English or Spanish. It reads, it explains, and it changes nothing without a clear yes. - Every verdict carries the real line it came from. If Dante cannot read the proof, the verdict is unknown . It never says safe on an assumption. - Silent by default. No telemetry, no background update check, no account. The free state runs fully offline. - Zero dependencies. One small Node.js program you can read. The source is public https://github.com/Mira12D/dante-watch-Antivirus-against-AI-Agents . What it checks - Secrets lying around https://ai-agent-antivirus.space/find-leaked-api-keys/ : API keys, tokens and private keys in project files, .env files and Git history, matched against a library of 1,111 secret formats. It shows file, line and kind - never the value. - Your servers https://ai-agent-antivirus.space/is-my-server-hacked/ : SSH settings, world-writable files in web folders, known PHP vulnerabilities by version, signs of web shells. - AI agent configuration https://ai-agent-antivirus.space/ai-agent-security-risks/ : MCP server entries and agent settings with the optional Hugging Face analysis pack , reported without ever printing a key. - Bait files https://ai-agent-antivirus.space/canary-tokens-bait-files/ the "Wachschutz" : fake credentials that mail you the moment someone uses them. - Windows: services anyone can overwrite, unquoted service paths, writable PATH folders, AlwaysInstallElevated, stored autologon passwords. Is it any good? An honest answer Dante is young. It is a watchman, not a real-time engine: it looks when you ask or on the schedule you agreed to, and it does not scan running processes for malware. What it does well is the boring, high-value part: finding the secrets and settings an attacker or a hijacked agent would use first, and refusing to claim more than it can prove. Its language layer what you type is trained on about 259,000 labelled sentences and answers "I don't know" instead of guessing when unsure. Four steps, each one small You never have to decide everything now. Start with step 1. Dante asks before every next thing, and every question shows the exact command first. Start in three minutes Install Node.js nodejs.org, once , open a terminal, paste one line: npx dante-watch Same program, same words, on every system. Not sure where your terminal is? The install page https://ai-agent-antivirus.space/install-dante/ shows it for Mac, Windows and Linux, step by step. Details for every system, the free and paid parts and what each costs are on the install page https://ai-agent-antivirus.space/install-dante/ . Before you close this tab Look, nobody wakes up wanting to audit their laptop. It is boring, it feels like homework, and it always looks fine until the day it does not. So here is the deal. It takes three minutes. It only reads. It costs nothing. If it finds nothing, you wasted three minutes and you can say you checked. If it finds a key lying around, you found it before somebody else did. Your agent has the keys to your house either way. The only question is whether you know which keys. npx dante-watch Check your own machine now Install Node.js, open a terminal, type npx dante-watch . Step-by-step for Mac, Windows and Linux https://ai-agent-antivirus.space/install-dante/ . Nothing to lose by looking. Dante only reads. It asks before every change and shows the command first. No account. Delete the folder ~/.dante and it is gone. Questions people ask Do AI agents need antivirus? They need protection, but not the kind that matches malware signatures. An agent is legitimate software running with your rights. What matters is which secrets and servers it can reach and whether anything can instruct it. Checking where secrets lie, how SSH is set and what the agent configuration allows covers the real exposure. Is Dante an antivirus? No. Dante is a watchman for machines you own. It does not scan for malware in real time. It finds exposed secrets, risky settings and known vulnerabilities, and shows the proof line for each result. Does Dante send my data anywhere? No. By default it sends nothing. Only three actions use the network update, the catalog, and the optional bait watch and each starts only after you answer yes to the command Dante prints first. Is it free? Yes. The free state is complete and works offline. Extra knowledge packs and the bait watch are optional; prices are on the install page.