Computer Use Linux
Linux desktop control over MCP — AT-SPI, GNOME Shell, Wayland portals, ydotool
Is Computer Use Linux safe? Promising trust profile, but some evidence still deserves review.
Compare Computer Use Linux
How does it stack up against its Agent Skills neighbours?
Pick any agent to compare →In detail: Computer Use Linux scores 73.0/100 (Grade B), ranked #27 of 371 tracked open-source AI agent projects, on evidence coverage B (3 of 5 independent signal types). The public evidence: no package-provenance attestation found; OSSF Scorecard rates its supply-chain practices 6.5/10; 84% of recent commits are signed; no published advisory affects its latest release (@agent-sh/computer-use-linux); last pushed 2026-10-10. Every point is earned from checkable signals — never paid placement. How scoring works →
How Computer Use Linux could raise its score
Each line changes one public signal and recomputes with the live scoring function. The gains don't add up exactly, because the score is capped near the top.
- Publish build provenance for its packagesnpm publish --provenance from CI +14.1 → 87.1 A · #7 of 371
- Raise the OSSF Scorecard from 6.5 to 9.0lowest checks: Branch-Protection 0, CII-Best-Practices 0, Fuzzing 0 +5.2 → 78.2 B · #20 of 371
- Sign every commit84% signed today +0.8 → 73.8 B · #27 of 371
Chain of custody
Scanners check what the code says. This traces who ships Computer Use Linux and whether that has changed: from the source repository, through how changes are reviewed and released, to the package you install. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities and, for skills, AST02 Supply Chain Compromise.
-
Source Signed
github.com/agent-sh/computer-use-linux, MIT, last pushed 2026-10-10. 84% of the last 100 commits carry a verified signature, so changes trace to a verified account.
-
Review and release Mixed
OpenSSF Scorecard rates the repository's practices 6.5/10 (scanned Oct 3, 2026). The checks that decide who can get a change released:
- Code Review9
- Branch Protection0
- Signed Releases0
- Dangerous Workflow10
- Token Permissions10
- Pinned Dependencies6
All 18 Scorecard checks
Binary-Artifacts 10Branch-Protection 0CI-Tests 10CII-Best-Practices 0Code-Review 9Contributors 10Dangerous-Workflow 10Dependency-Update-Tool 10Fuzzing 0License 10Maintained 10Packaging 10Pinned-Dependencies 6SAST 9Security-Policy 4Signed-Releases 0Token-Permissions 10Vulnerabilities 0 -
Published packages Linked, not attested
- npm @agent-sh/computer-use-linux Source link points back to this repo No build attestation
Without a build attestation, nothing proves the published files were built from this repository.
-
What you install today No known advisories
Latest release checked: @agent-sh/computer-use-linux 0.7.13. No published advisory affects it (OSV, checked 2026-10-10).
Changes to this chain
- 2026-08-31 OSSF Scorecard: 6.7/10
Evidence behind this score
Coverage B: 3 of 5 independent evidence types found.
- GitHub repository data
- Package downloads
- Supply-chain checks
- Public actions (missing)
- Community mentions (missing)
Verify this score yourself
Every build re-issues Computer Use Linux’s score as an Ed25519-signed credential, valid for 7 days. You can check it offline against HVTracker’s published key; if anyone changes a number after signing, verification fails.
What this score doesn’t check
It covers who ships the code, not what the code does. It doesn’t read the skill’s instructions for injected instructions, watch runtime behaviour, or find bugs nobody has disclosed yet. For that, run a content scanner before you install it, such as Cisco Skill Scanner.
How Computer Use Linux compares in Agent Skills
- #25 Openmed 74.8 +1.8
- #26 Memsearch 74.5 +1.5
- #27 Computer Use Linux 73.0 this agent
- #28 Dev Browser 72.4 −0.6
- #29 Arcgentic 70.7 −2.3
Bars show each HVTrust score; the tick marks Computer Use Linux’s 73.0.
Where the 73.0 comes from
HVTrust dimensions vs the Agent Skills average
73.0 / 100 · 100.0% confidenceComputer Use Linux Agent Skills average (371 agents)
Quick Trust Read
How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade B reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage B is separate — it grades how many independent signal types back the score (3 of 5), so a high score on thin evidence stays visible. Full methodology →
Rank Trend
Activity & Reach
Analysis
Activity Inputs
73.3 / 100Common questions about Computer Use Linux
Does Computer Use Linux publish package provenance?
Does Computer Use Linux have an OpenSSF Scorecard?
Is Computer Use Linux actively maintained?
What license does Computer Use Linux use?
Are Computer Use Linux's commits signed?
Not a safety endorsement. HVTracker describes what public signals show, not whether a project is safe for your use case. Run your own security review before adopting in production.
AI agent surface
MCP, providers, tool surface
These runtime-trust fields — detected from public repo docs and manifests — contribute a bounded adjustment to this project's HVTrust score alongside supply-chain evidence. The exact values each field can add or subtract are documented in the methodology → Compare this surface across every listed agent in the capability matrix →
- MCP signal live
- External deps live
- Tool / plugin surface live
- Package provenance drift live
Detected changes to Computer Use Linux's runtime surface and supply-chain posture, from daily public-signal snapshots. A change here means our detectors see something different — a genuinely changed capability, or better evidence of an existing one.
Maintain Computer Use Linux?
For maintainers
HVTrust scores Computer Use Linux from public signals only — we never contact maintainers first. If a signal is wrong, stale, or missing (provenance you publish, a Scorecard you run, signed releases), tell us and we'll review it. Corrections are public and tracked on GitHub.
Reputation Timeline
Signal history
Embed Badge Badge guide for maintainers →
For maintainers
[](https://hvtracker.net/agents/computer-use-linux)
<a href="https://hvtracker.net/agents/computer-use-linux"><img src="https://hvtracker.net/badge/computer-use-linux.svg" alt="HVTrust"></a>
Other agents in Agent Skills
GitHub REST API (repo, commits, stars, forks, license) · npm Registry (downloads, provenance) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON