agent-desktop@r1
VERIFIED· install onlyPublisher claims: "Enables AI agents to control a Linux desktop and browser through governed tools for mouse, keyboard, windows, clipboard, screenshots, navigation, and page interaction, with policy verdicts, human confirmation, secret redaction, and an append-only audit trail." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
OPENROUTER_API_KEY- Where it talks to
- no vendor host named in the codeAlso openrouter.ai — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- use of the skill by an agent
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names openrouter.ai as well as its own vendor. The guard injects OPENROUTER_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is agent-desktop@r1 safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-13 and scored it 88/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.name = subprocess.check_output(["xdotool", "getwindowname", wid], env=self._env(), text=True, timeout=2).strip()Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.self.xephyr_process = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."""Activate the kill switch. All desktop/browser tools will refuse until the sentinel file is removed."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.return Decision(action, "deny", "kill switch is active")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.ids = subprocess.check_output(["xdotool", "search", "--name", ""], env=self._env(), text=True, timeout=5).splitlines()Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.