Cua
Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.
Is Cua safe? Strong public trust posture, backed by multiple independent signals.
Compare Cua
How does it stack up against its Browser & Computer Use neighbours?
Pick any agent to compare →In detail: Cua scores 77.5/100 (Grade B), ranked #198 of 1371 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 5.9/10; 98% of recent commits are signed; no published advisory affects its latest release (cua); last pushed 2026-10-09. Every point is earned from checkable signals — never paid placement. How scoring works →
How Cua 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 packagesPyPI Trusted Publishing attestations +12.6 → 90.1 A · #3 of 45
- Raise the OSSF Scorecard from 5.9 to 9.0lowest checks: CII-Best-Practices 0, Code-Review 0, SAST 0 +6.5 → 84.0 A · #8 of 45
Chain of custody
Scanners check what the code says. This traces who ships Cua 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.
-
Source Signed
github.com/trycua/cua, MIT, last pushed 2026-10-09. 98% 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 5.9/10 (scanned Oct 8, 2026). The checks that decide who can get a change released:
- Code Review0
- Branch Protection3
- Signed Releases3
- Dangerous Workflow10
- Token Permissions0
- Pinned Dependencies5
All 18 Scorecard checks
Binary-Artifacts 10Branch-Protection 3CI-Tests 10CII-Best-Practices 0Code-Review 0Contributors 10Dangerous-Workflow 10Dependency-Update-Tool 10Fuzzing 10License 10Maintained 10Packaging 10Pinned-Dependencies 5SAST 0Security-Policy 10Signed-Releases 3Token-Permissions 0Vulnerabilities 0 -
Published packages Linked, not attested
- PyPI cua 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: cua 0.4.1. No published advisory affects it (OSV, checked 2026-10-09).
Changes to this chain
No change to package provenance, package source links, Scorecard coverage or license in HVTracker's daily snapshots of Cua.
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 Cua’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 tool descriptions or prompts for injected instructions, watch runtime behaviour, or find bugs nobody has disclosed yet. For that, run a content scanner before you connect it, such as Cisco MCP Scanner or Snyk Agent Scan.
How Cua compares in Browser & Computer Use
- #8 Camofox Browser 81.4 +3.9
- #9 agent-device 78.7 +1.2
- #10 Cua 77.5 this agent
- #11 Browser4 74.8 −2.7
- #12 Browser Use 71.6 −5.9
Bars show each HVTrust score; the tick marks Cua’s 77.5.
Where the 77.5 comes from
HVTrust dimensions vs the Browser & Computer Use average
77.5 / 100 · 100.0% confidenceCua Browser & Computer Use average (45 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
92.2 / 100Common questions about Cua
Does Cua publish package provenance?
Does Cua have an OpenSSF Scorecard?
Is Cua actively maintained?
What license does Cua use?
Are Cua'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 Cua'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 Cua?
For maintainers
HVTrust scores Cua 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/cua)
<a href="https://hvtracker.net/agents/cua"><img src="https://hvtracker.net/badge/cua.svg" alt="HVTrust"></a>
Other agents in Browser & Computer Use
GitHub REST API (repo, commits, stars, forks, license) · PyPI / pypistats (downloads, provenance) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON