open-computer-use@1.1.5
VERIFIED· install onlyPublisher claims: "Cross-platform Computer Use MCP server launcher. After install, configure open-computer-use mcp." Observed in sandbox: reads credential files.
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.
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 1.1.5This 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 scenariosStatic findings
printEvaluation(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.printEvaluation(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.printEvaluation({ 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.printEvaluation(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.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
Not checked against OSV yet; the weekly check has not reached this version.