Skills/npm/open-computer-use

open-computer-use@1.1.5

VERIFIED· install only

Publisher claims: "Cross-platform Computer Use MCP server launcher. After install, configure open-computer-use mcp." Observed in sandbox: reads credential files.

Registry npm (MCP server)Publisher ifuryst · publishing for 217 daysInstalls 54,983Last detonated 46 min ago
$claude mcp add open-computer-use -- npx -y open-computer-use
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 8 of 16 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · 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
no credential variables read in the code
Where it talks to
no vendor host named in the code
What we saw when it ran
read ~/.npmrc · no network
What we could not test
use of the skill by an agent

Connect it only under the guard, with no real credential files on the machine it runs on. It read ~/.npmrc, which is nothing an MCP server needs from a user. `--contain` makes those directories unreadable.

$vet-skills run --contain --net declared -- npx -y open-computer-use

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 1.1.4

vet-skills diff open-computer-use 1.1.4 1.1.5

This version reaches for something 1.1.4 did not: 1 new credential file (~/.npmrc) · 1 new install script (node ./scripts/postinstall.mjs). Compared from the two recorded runs, not from source.

New credential files
~/.npmrc
New install scripts
node ./scripts/postinstall.mjs

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 85/100 (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: reads credential files.

Behavior trace

Honeypot run · 1 s · 3 scenarios
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.1sprocessbundled script run in the sandbox with no arguments
0.2sfilesystemwrote ~/.claude.json
0.2sprocessexec /usr/bin/dirname
0.2sprocessbundled script run in the sandbox with no arguments
0.4sfilesystemwrote ~/.codex/config.toml
0.4sprocessexec /usr/bin/dirname
0.4sprocessexec /usr/bin/mkdir
0.4sprocessbundled script run in the sandbox with no arguments
0.6sprocessexec /usr/bin/dirname
0.6sprocessexited 1: Missing runnable Linux binary for linux-x64.
0.6sprocessbundled script run in the sandbox with no arguments
0.6sprocessexited 1: (Use `node --trace-warnings ...` to show where the warning was created)
0.6sprocessbundled script run in the sandbox with no arguments
0.9sfilesystemread ~/.npmrc
0.9sfilesystemread ~/.npm/_logs outside project
0.9sprocessexec /usr/bin/dirname
0.9sprocessexec /usr/local/bin/npm
0.9sprocessexec /usr/bin/cat
0.9sprocessexited 1: an absolute path.
0.9sprocessbundled script run in the sandbox with no arguments
1.0sprocessexec /usr/bin/dirname
1.0sprocessbundled script run in the sandbox with no arguments
1.2sfilesystemwrote ~/.config/opencode/opencode.json
1.2sprocessexec /usr/bin/dirname
1.2sprocessbundled script run in the sandbox with no arguments · not named in the instructions
1.3sprocess8 of 16 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
1.3sprocessscript backend runs setup only
1.3sprocessscript backend runs setup only
1.3sprocesssecond launch, clock +45 days, CI unset

Static findings

MEDIUM
File type combined with upload actionscripts/node-repl/open-computer-use-cli.mjs:366 · File type combined with upload action — agent may exfiltrate local data filesprintEvaluation(result, { json: options.json, output });Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/node-repl/open-computer-use-cli.mjs:395 · File type combined with upload action — agent may exfiltrate local data filesprintEvaluation(result, { json: options.json, output });Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/node-repl/open-computer-use-cli.mjs:392 · File type combined with upload action — agent may exfiltrate local data filesprintEvaluation({ content: [{ type: "text", text: "Open Computer Use JavaScript session reset" }], isError: false }, { json: options.json, output });Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/node-repl/open-computer-use-cli.mjs:339 · File type combined with upload action — agent may exfiltrate local data filesprintEvaluation(result, { json: options.json, output });Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈1,656 tok
1 file · 30 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.