unifly
unifly is a Rust CLI for managing Ubiquiti UniFi network infrastructure.
Examining code for the line that is wrong
What it does
unifly is a Rust CLI for managing Ubiquiti UniFi network infrastructure. It unifies the modern Integration API (REST, API key), the Session API (cookie plus CSRF), and Site Manager cloud APIs behind a single coherent interface, plus real-time WebSocket event streaming.
Read more
28 top-level commands cover devices and switch port config-as-code, clients, networks, WiFi, firewall policies, zones, and groups, NAT policies, ACLs, DNS, traffic matching lists, hotspot vouchers, DPI, stats, backups, the full VPN surface, site settings, cloud fleet queries, and a raw API escape hatch.
This skill should be used when the user asks to "manage UniFi devices", "configure UniFi networks", "create a VLAN", "provision an SSID",…
You don’t need to name it. Ask for the job in your own words — your AI loads the skill when the request matches.
What it can touch
No script files in its folder
Its folder holds text, not programs — but the instructions do tell your AI to run commands (see below).
How we know
Listed the 15 files in the skill’s folder on GitHub; none is a script or program.
Asks for an API key or token
You will need an account with the service it talks to, and your own key. Keep keys in your settings or environment, never in a chat.
How we know
The SKILL.md names UNIFI_API_KEY, UNIFI_PASSWORD.
Installs other software
Following it will install packages (npm, pip, brew or similar). Those come from their own publishers, not from this skill.
How we know
The SKILL.md contains package-install commands.
Its code sends data over the internet
A script in it uploads or posts data. That is normal for a skill that talks to a service — check that the address is the service you expect.
How we know
references/workflows.md line 190: “curl -fsSL -X POST "$SLACK_WEBHOOK" -H "Content-Type: application/json" -d "{\"text\": $(echo "$event" | jq '.message')}"”. Read 2026-10-05, commit b565654.
references/workflows.md, line 190 ↗1 smaller thing worth knowing
Tells your AI to open private keys or password stores. Usually legitimate — listed so nothing is hidden.
How we know
Tells your AI to open private keys or password stores — references/commands.md line 769. Read 2026-10-05, commit b565654.
references/commands.md, line 769 ↗No serious risk pattern found
Launch7’s automated check read all 15 text files in this skill and matched none of its serious risk patterns. This is not a guarantee: a check like this can miss new or disguised tricks, and the author can change the files after the check.
How we know
Read 2026-10-05, commit b565654 by pipeline/trust/analyze.py — 40+ patterns for hidden text, prompt injection, downloads that run, credential access and more. It reads; it never runs the skill.
Recently maintained
Its repository has had changes recently.
How we know
Last push to hyperb1iss/unifly: 2026-08-07 (59 days before the scan).
Read automatically from the skill’s own files on GitHub on 5 Oct 2026. Launch7 does not run or manually review skills: this lists what the check saw, and nothing here means “safe”. How we check
Add it to your AI
Supported. Upload it once in Claude’s settings. Works on every plan, including Free.
Built in your browser from the SKILL.md on GitHub — nothing passes through Launch7.
In Claude, open Customize → Skills, press +, then Create skill → Upload a skill, and choose the .zip.
Make sure code execution is switched on (Settings → Capabilities). Skills need it.
Start a new chat and ask for the job in your own words — Claude picks the skill up when it fits.
How Claude does this: support.claude.com · checked 28 Sep 2026 · “Supported” means documented by the vendor; Launch7 has not run it end to end