Open-source runtime verification for AI, licensed under Apache-2.0.
QWED
Contact

Type to search pages, engines and advisories.

    Looking for API details?Search the docs

    GitHub Action

    QWED checks in your own CI workflows.

    A GitHub Action that scans for leaked secrets, unsafe code and dangerous shell scripts on the runner, and can verify model output against a QWED API.

    At a glance

    Use
    QWED-AI/qwed-verification-action@v1
    Listed on
    GitHub Marketplace, verified publisher
    Output
    Text, JSON, SARIF or a Verification Context
    Data
    Scan modes never leave the runner
    Licence
    Apache-2.0

    Modes

    • scan-secrets

      Leaked secrets

      API keys, tokens and SSH keys.

    • scan-code

      Unsafe code

      eval(), exec(), subprocess and unsafe imports.

    • verify-shell

      Dangerous scripts

      curl | bash, rm -rf and sudo escapes.

    • verify

      Model output

      Math, logic, SQL and code in model output, checked by a QWED API.

    • verify-process

      Reasoning steps

      Traces must follow Issue, Rule, Application, Conclusion and hit the milestones you list.

    Get started

    .github/workflows/qwed.yml
    name: QWED Verificationon: [pull_request]jobs:  verify:    runs-on: ubuntu-latest    steps:      - uses: actions/checkout@v4      - uses: QWED-AI/qwed-verification-action@v1        with:          action: scan-secrets          paths: "**/*.env,**/*.json"          output_format: sarif          fail_on_findings: "true"

    Good to know

    • scan-secrets, scan-code, verify-shell and verify-process run entirely inside the runner.
    • verify calls a QWED API: pass an api_key, or point api_url at your own deployment.
    Use case: Software deliveryQWED Security checks every code change on GitHub before it merges.

    More developer tools