Is Qwen Agent safe to use?

Qwen Agent has an HVTrust score of 50.1/100 (Grade C), ranked #957 of 1371 tracked AI agent projects. This score reflects verifiable supply-chain integrity, transparency, maintenance, and adoption signals.

What is the trust score for Qwen Agent?

Qwen Agent scores 50.1/100 on HVTracker's evidence-weighted HVTrust scale. It has 17.2k GitHub stars and is categorized under Agent Frameworks.

Qwen Agent

Repository by QwenLM

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

Agent Frameworks Python Listed Apache-2.0

Is Qwen Agent safe? Thin or incomplete trust evidence. Review carefully before production use.

OSSF Scorecard 4.4 / 10

Provenance None

Signed commits 14%

Last push 219d ago

Advisories None known

Compare Qwen Agent

How does it stack up against its Agent Frameworks neighbours?

Pick any agent to compare →

Suggest a correction

In detail: Qwen Agent scores 50.1/100 (Grade C), ranked #957 of 1371 tracked open-source AI agent projects, on evidence coverage A (4 of 5 independent signal types). The public evidence: no package-provenance attestation found; OSSF Scorecard rates its supply-chain practices 4.4/10; 14% of recent commits are signed; no published advisory affects its latest release (qwen-agent); last pushed 2026-03-04. Every point is earned from checkable signals — never paid placement. How scoring works →

How Qwen Agent 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 +14.7 → 64.8 C · #42 of 129
Raise the OSSF Scorecard from 4.4 to 9.0lowest checks: CII-Best-Practices 0, Fuzzing 0, Maintained 0 +9.7 → 59.8 C · #61 of 129
Sign every commit14% signed today +4.3 → 54.4 C · #77 of 129

Already done? Suggest a correction Add the trust badge

Chain of custody

Scanners check what the code says. This traces who ships Qwen Agent 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 Partly signed

github.com/QwenLM/Qwen-Agent, Apache-2.0, last pushed 2026-03-04. 14% of the last 100 commits carry a verified signature; the rest can't be tied to a verified identity.
Review and release Mixed

OpenSSF Scorecard rates the repository's practices 4.4/10 (scanned Oct 9, 2026). The checks that decide who can get a change released:
- Code Review1
- Branch Protectionn/a
- Signed Releasesn/a
- Dangerous Workflow10
- Token Permissions10
- Pinned Dependencies1
All 14 Scorecard checks

Binary-Artifacts 10

Branch-Protection -1

CII-Best-Practices 0

Code-Review 1

Dangerous-Workflow 10

Fuzzing 0

License 10

Maintained 0

Packaging -1

Pinned-Dependencies 1

SAST 0

Security-Policy 0

Signed-Releases -1

Token-Permissions 10
Published packages Linked, not attested
- PyPI qwen-agent 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: qwen-agent 0.0.34. 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 Qwen Agent.

Evidence behind this score

Coverage A: 4 of 5 independent evidence types found.

GitHub repository data
Package downloads
Supply-chain checks
Public actions (missing)
Community mentions

Verify this score yourself

Every build re-issues Qwen Agent’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.

Signed credential (JSON) How to verify

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 Qwen Agent compares in Agent Frameworks

Bars show each HVTrust score; the tick marks Qwen Agent’s 50.1.

Where the 50.1 comes from

HVTrust dimensions vs the Agent Frameworks average

50.1 / 100 · 100.0% confidence

Qwen Agent Agent Frameworks average (129 agents)

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

6.2 / 25

3.3 below avg 9.5

Identity / Provenance60% listing status · 40% build provenance

10.8 / 18

0.8 below avg 11.6

Transparency50% declared license · 50% OSSF Scorecard

12.2 / 17

in line with avg 12.0

Maintenance60% last-push freshness · 40% commit activity

0 / 20

13.6 below avg 13.6

AdoptionLog-scaled stars · package downloads

15.9 / 20

5.1 above avg 10.8

Quick Trust Read

What Would Improve It

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

Recent Changes

2026-10-09

Grade Changed

Trust grade D → C

2026-10-09

Rank Moved

Rank rose 45 spots (#1002 → #957)

2026-09-28

Grade Changed

Trust grade C → D

Maintainer Checklist

Raise Scorecard signals Current OSSF Scorecard is 4.4/10. 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.

Increase signed commits Raise the share of verified-signed commits to make maintainer identity and release history easier to trust.

Refresh maintenance signals The repo was last pushed 219 days ago. Fresh activity helps separate stable projects from stale ones.

Compare with another agent Get email alerts for Qwen Agent View Agent Frameworks Report missing data

40.5

Activity sub-score · out of 100

#86

In Agent Frameworks

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 A is separate — it grades how many independent signal types back the score (4 of 5), so a high score on thin evidence stays visible. Full methodology →

Rank Trend

2026-09-29 2026-10-09

Activity & Reach

Stars

17.2k

Forks

1.7k

Last Push

2026-03-04

219 days ago

Commits (4 wk)

Downloads (7d)

18,572

pypi

HN mentions (30d)

Open Issues

434

Rank Change

▲45

was #1002

Analysis

Activity Inputs

40.5 / 100

StarsRepository reach

25.4 / 30

FreshnessLast push recency

0.0 / 25

ActivityRecent commits

0.0 / 25

CommunityFork signal

15.1 / 20

Common questions about Qwen Agent

Public trust evidence for Qwen Agent 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 Qwen Agent publish package provenance?

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

Does Qwen Agent have an OpenSSF Scorecard?

Qwen Agent has an OpenSSF Scorecard score of 4.4/10. 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 Qwen Agent actively maintained?

Stale. The repository has not been pushed to in 219 days. Consider whether the project is still being maintained.

What license does Qwen Agent use?

Qwen Agent ships under Apache-2.0. A declared, OSI-approved license is one of the transparency signals HVTrust scores.

Are Qwen Agent's commits signed?

14% of the last 100 commits to Qwen Agent 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

medium confidence

Implemented

Qwen Agent appears to expose MCP server capabilities.

Detailed evidence is not shown in the public view.

External Service Dependencies

high confidence

1 detected

Public provider/service dependencies detected.

OpenAI

Credential signal: API keys or service config markers documented.

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

Maintain Qwen Agent?

For maintainers

HVTrust scores Qwen Agent 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

2026-10-09

Grade Changed

Trust grade D → C

2026-10-09

Rank Moved

Rank rose 45 spots (#1002 → #957)

2026-09-28

Grade Changed

Trust grade C → D

2026-09-28

Rank Moved

Rank dropped 44 spots (#929 → #973)

2026-09-25

Grade Changed

Trust grade D → C

2026-09-25

Rank Moved

Rank rose 37 spots (#967 → #930)

2026-09-24

Grade Changed

Trust grade C → D

2026-09-24

Rank Moved

Rank dropped 48 spots (#919 → #967)

2026-09-23

Grade Changed

Trust grade D → C

2026-09-23

Rank Moved

Rank dropped 548 spots (#371 → #919)

2026-09-22

Rank Moved

Rank dropped 40 spots (#331 → #371)

2026-09-21

Rank Moved

Rank rose 637 spots (#968 → #331)

2026-09-16

Rank Moved

Rank rose 10 spots (#969 → #959)

2026-09-11

Rank Moved

Rank dropped 10 spots (#946 → #956)

2026-09-09

Rank Moved

Rank dropped 12 spots (#936 → #948)

2026-09-08

Rank Moved

Rank dropped 13 spots (#923 → #936)

2026-09-07

Rank Moved

Rank dropped 38 spots (#885 → #923)

2026-09-06

Rank Moved

Rank dropped 17 spots (#868 → #885)

2026-09-05

Rank Moved

Rank dropped 55 spots (#813 → #868)

2026-09-04

Rank Moved

Rank dropped 40 spots (#773 → #813)

2026-09-03

Rank Moved

Rank dropped 28 spots (#745 → #773)

2026-09-02

Rank Moved

Rank dropped 30 spots (#715 → #745)

2026-09-01

Rank Moved

Rank dropped 30 spots (#685 → #715)

2026-08-31

Rank Moved

Rank dropped 38 spots (#647 → #685)

2026-08-30

Rank Moved

Rank dropped 17 spots (#630 → #647)

2026-08-29

Rank Moved

Rank dropped 41 spots (#589 → #630)

2026-08-28

Rank Moved

Rank dropped 19 spots (#570 → #589)

2026-08-27

Rank Moved

Rank dropped 14 spots (#556 → #570)

2026-08-26

Rank Moved

Rank dropped 84 spots (#472 → #556)

2026-08-24

Rank Moved

Rank dropped 15 spots (#457 → #472)

2026-08-22

Rank Moved

Rank rose 13 spots (#472 → #459)

2026-08-19

Rank Moved

Rank dropped 10 spots (#462 → #472)

2026-08-17

Rank Moved

Rank rose 10 spots (#470 → #460)

2026-08-13

Rank Moved

Rank dropped 14 spots (#445 → #459)

2026-08-12

Rank Moved

Rank rose 15 spots (#460 → #445)

2026-08-10

Grade Changed

Trust grade C → D

2026-08-10

Rank Moved

Rank dropped 17 spots (#444 → #461)

2026-08-08

Rank Moved

Rank dropped 110 spots (#329 → #439)

2026-07-29

Rank Moved

Rank dropped 10 spots (#312 → #322)

2026-07-18

Grade Changed

Trust grade C → D

2026-07-15

Rank Moved

Rank dropped 22 spots (#278 → #300)

2026-07-14

Rank Moved

Rank dropped 14 spots (#264 → #278)

2026-07-13

Rank Moved

Rank dropped 32 spots (#232 → #264)

GitHub → PyPI: qwen-agent

Embed Badge Badge guide for maintainers →

For maintainers

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

Other agents in Agent Frameworks

Data sources
GitHub REST API (repo, commits, stars, forks, license) · PyPI / pypistats (downloads, provenance) · OpenSSF Scorecard CLI · Algolia HN Search API
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON

Qwen Agent

How Qwen Agent could raise its score

Chain of custody

Source Partly signed

Review and release Mixed

Published packages Linked, not attested

What you install today No known advisories

Changes to this chain

Evidence behind this score

Verify this score yourself

What this score doesn’t check

How Qwen Agent compares in Agent Frameworks

Where the 50.1 comes from

HVTrust dimensions vs the Agent Frameworks average

Quick Trust Read

Rank Trend

Activity & Reach

Analysis

Activity Inputs

Common questions about Qwen Agent

AI agent surface

Maintain Qwen Agent?

Reputation Timeline

Embed Badge Badge guide for maintainers →

Other agents in Agent Frameworks