Is agent-device safe to use?

agent-device has an HVTrust score of 50.4/100 (Grade C), ranked #769 of 1320 tracked AI agent projects. This score reflects verifiable supply-chain integrity, transparency, maintenance, and adoption signals.

What is the trust score for agent-device?

agent-device scores 50.4/100 on HVTracker's evidence-weighted HVTrust scale. It has 4.3k GitHub stars and is categorized under Browser & Computer Use.

agent-device

callstack/agent-device

Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, Ha

Browser & Computer Use TypeScript Grade C Listed MIT

50.4/100

Rank #769 of 1320

Compare agent-device

How does it stack up against its Browser & Computer Use neighbours?

Pick any agent to compare →

Thin or incomplete trust evidence. Review carefully before production use.

Open compare tool Suggest correction

Listing state

Listed

Evidence coverage

Grade C · 2/5 signals

Last push

2026-09-04 · 0d ago

Recent change

Rank +14

Is agent-device safe? agent-device scores 50.4/100 (Grade C), ranked #769 of 1320 tracked open-source AI agent projects, on evidence coverage C (2 of 5 independent signal types). The public evidence: no package-provenance attestation found; OSSF Scorecard rates its supply-chain practices 6.5/10; 100% of recent commits are signed; last pushed 2026-09-04. Every point is earned from checkable signals — never paid placement. How scoring works →

Ranked neighbours in Browser & Computer Use

#21 openocta — 51.1 (C) → #22 Open Computer Use — 50.8 (C) → #24 Camofox Browser — 50.4 (C) → #25 Peekaboo — 49.3 (D) →

Quick Trust Read

What Would Improve It

Publish package provenance or release attestations for stronger supply-chain evidence.

Recent Changes

2026-09-04

Rank Moved

Rank dropped 26 spots (#743 → #769)

2026-09-03

Grade Changed

Trust grade D → C

2026-09-03

Rank Moved

Rank dropped 36 spots (#707 → #743)

Maintainer Checklist

Raise Scorecard signals Current OSSF Scorecard is 6.5/10. Tighten the weakest checks to improve public safety evidence.

Publish provenance Add package provenance or release attestations so users can verify where shipped artifacts came from.

Compare with another agent Get email alerts for agent-device View Browser & Computer Use Report missing data

83.1

Activity sub-score · out of 100

#23

In Browser & Computer Use

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade C reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage C is separate — it grades how many independent signal types back the score (2 of 5), so a high score on thin evidence stays visible. Full methodology →

Rank Trend

2026-08-11 2026-09-04

Activity & Reach

Stars

4.3k

Forks

272

Last Push

2026-09-04

today

Commits (4 wk)

445

Downloads (7d)

—

HN mentions (30d)

—

Open Issues

Rank Change

▼26

was #743

Analysis

HVTrust Dimensions vs Browser & Computer Use

50.4 / 100 · 67.0% confidence

agent-device Browser & Computer Use average (41 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits

13.1 / 25

3.8 above avg 9.3

Identity / Provenance60% listing status · 40% build provenance

10.8 / 18

1.6 below avg 12.4

Transparency50% declared license · 50% OSSF Scorecard

14.0 / 17

2.3 above avg 11.7

Maintenance60% last-push freshness · 40% commit activity

20.0 / 20

7.0 above avg 13.0

AdoptionLog-scaled stars · package downloads

8.7 / 20

1.7 below avg 10.4

Activity Inputs

83.1 / 100

StarsRepository reach

21.8 / 30

FreshnessLast push recency

25.0 / 25

ActivityRecent commits

25 / 25

CommunityFork signal

11.3 / 20

Supply Chain Trust

Package Provenance

None

No package attestations found

OSSF Scorecard

6.5 / 10

OpenSSF Scorecard · scanned Sep 3, 2026

Signed Commits

100%

of last 100 commits verified

Binary-Artifacts 9

Branch-Protection 3

CI-Tests 10

CII-Best-Practices 0

Code-Review 0

Contributors 10

Dangerous-Workflow 10

Dependency-Update-Tool 10

Fuzzing 10

License 10

Maintained 10

Packaging -1

Pinned-Dependencies 9

SAST 10

Security-Policy 10

Signed-Releases 0

Token-Permissions 0

Vulnerabilities 6

Is agent-device safe?

Public trust evidence for agent-device is thin: several supply-chain signals are missing or weak. This does not mean the project is unsafe — it means an outside observer cannot easily verify the usual integrity checks. Treat with extra scrutiny.

Does agent-device publish package provenance?

No published build provenance is currently detected for agent-device. This is common for open-source projects but means consumers cannot independently verify that the package on the registry matches the GitHub source.

Does agent-device have an OpenSSF Scorecard?

agent-device has an OpenSSF Scorecard score of 6.5/10. The Scorecard checks for branch protection, signed releases, dependency updates, fuzzing, code review, and other supply-chain hygiene items. See the full check breakdown on this page.

Is agent-device actively maintained?

Actively maintained. The repository was pushed to within the last 1 day(s).

What license does agent-device use?

agent-device ships under MIT. A declared, OSI-approved license is one of the transparency signals HVTrust scores.

Are agent-device's commits signed?

100% of the last 100 commits to agent-device are verified-signed (GPG, SSH, S/MIME, or GitHub's signing flow). Signed commits help confirm that code was authored by who the commit claims.

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

Scored in HVTrust

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 Server Support

high confidence

Implemented

agent-device appears to expose MCP server capabilities.

Detailed evidence is not shown in the public view.

External Service Dependencies

None detected

No clear third-party provider dependency detected.

Credential signal: No explicit API-key/config marker detected.

Tool / Plugin Surface

None detected

No clear plugin system or broad tool surface detected.

Detailed evidence is not shown in the public view.

Package Provenance Drift

high confidence

Match

Published package metadata matches the tracked repo

Detailed evidence is not shown in the public view.

MCP signal live
External deps live
Tool / plugin surface live
Package provenance drift live

How this surface has changed

Detected changes to agent-device'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.

2026-08-12

Provider Removed

Runtime surface shrank — no longer detected: Anthropic

Maintain agent-device?

For maintainers

HVTrust scores agent-device 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.

Submit a correction → Add the trust badge

Reputation Timeline

Signal history

2026-09-04

Rank Moved

Rank dropped 26 spots (#743 → #769)

2026-09-03

Grade Changed

Trust grade D → C

2026-09-03

Rank Moved

Rank dropped 36 spots (#707 → #743)

2026-09-02

Grade Changed

Trust grade B → D

2026-09-02

Rank Moved

Rank dropped 604 spots (#103 → #707)

2026-09-02

HVTrust Changed

HVTrust down 29.4pts (79.3 → 49.9)

2026-08-31

Grade Changed

Trust grade C → B

2026-08-31

Rank Moved

Rank rose 507 spots (#607 → #100)

2026-08-31

HVTrust Changed

HVTrust up 29.1pts (50.2 → 79.3)

2026-08-30

Scorecard Added

OSSF Scorecard: 6.4/10

2026-08-30

Grade Changed

Trust grade D → C

2026-08-30

Rank Moved

Rank rose 83 spots (#690 → #607)

2026-08-30

HVTrust Changed

HVTrust up 4.3pts (45.9 → 50.2)

2026-08-29

Rank Moved

Rank dropped 41 spots (#649 → #690)

2026-08-28

Rank Moved

Rank dropped 19 spots (#630 → #649)

2026-08-27

Rank Moved

Rank dropped 13 spots (#617 → #630)

2026-08-26

Rank Moved

Rank dropped 98 spots (#519 → #617)

2026-08-24

Rank Moved

Rank rose 281 spots (#803 → #522)

2026-08-24

HVTrust Changed

HVTrust up 18.7pts (27.2 → 45.9)

2026-08-22

Rank Moved

Rank dropped 278 spots (#525 → #803)

2026-08-22

HVTrust Changed

HVTrust down 18.5pts (45.7 → 27.2)

2026-08-19

Rank Moved

Rank rose 282 spots (#808 → #526)

2026-08-19

HVTrust Changed

HVTrust up 18.5pts (27.1 → 45.6)

2026-08-17

Rank Moved

Rank dropped 285 spots (#523 → #808)

2026-08-17

HVTrust Changed

HVTrust down 18.6pts (45.7 → 27.1)

2026-08-13

Rank Moved

Rank rose 277 spots (#791 → #514)

2026-08-13

HVTrust Changed

HVTrust up 18.6pts (27.1 → 45.7)

2026-08-12

Provider Removed

Runtime surface shrank — no longer detected: Anthropic

2026-08-12

Rank Moved

Rank dropped 274 spots (#517 → #791)

2026-08-12

HVTrust Changed

HVTrust down 18.4pts (45.5 → 27.1)

2026-08-10

Newly Listed

First tracked at rank #518

GitHub → npm: agent-device

Embed Badge Badge guide for maintainers →

For maintainers

Markdown:
            [![HVTrust](https://hvtracker.net/badge/agent-device.svg)](https://hvtracker.net/agents/agent-device)
            
HTML:
            <a href="https://hvtracker.net/agents/agent-device"><img src="https://hvtracker.net/badge/agent-device.svg" alt="HVTrust"></a>

Other agents in Browser & Computer Use

Data sources
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 v4.3 · Raw JSON