computer-use-linux@0.7.53
CAUTION· install onlyPublisher claims: "Native Linux desktop control for AI agents (MCP server, Pi tools, and CLI): semantic AT-SPI accessibility trees, screenshots, compositor window targeting, Wayland/X11 input, and an on-screen activity indicator." Observed in sandbox: sends data to release-assets.githubusercontent.com.
Coverage
Install scripts ran; no agent task scenario for this bundle.- Tested
- install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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: Caution 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 codeAlso githubusercontent.com — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · contacted release-assets.githubusercontent.com (undeclared)
- What we could not test
- use of the skill by an agent
Find out what these hosts are first. In the honeypot it contacted release-assets.githubusercontent.com, which nothing in the package names as its own. If that is the vendor's service, fine; if you cannot place it, do not connect it.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; install scripts ran; no agent task scenario for this bundle) on 2026-11-13 and scored it 71/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: sends data to release-assets.githubusercontent.com.
Behavior trace
Honeypot run · 1 s · 2 scenariosStatic findings
…}){let de=L.$comment;if(se.$comment===!0)T.code((0,a._)`${u.default.self}.logger.log(${de})`);else if(typeof se.$comment=="function"){let Ce=(0,a.str)`${ne}/$comment`,Ne=T.scopeValue("root",{ref:j.root});T.code((0,a._)`${u.default.self}.op…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.No other findings across 6,182 lines in 14 files.
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
No advisories in OSV for @agent-sh/computer-use-linux@0.7.53 as of 27 h ago. This is the package itself, not its dependencies.
What would make this Verified
9 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
- Unclaimed publisher≈ +8 on the totalClaim agent-sh: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.