Ask OSV about known vulnerabilities in your packages, right on the phone.

OSV is an open vulnerability database. With OSV connected, your agent can check whether a package, a specific version, or a commit is affected by known vulnerabilities, look up a vulnerability by its ID, and explain the severity and affected versions in plain language. Callers from your team or your customers get clear answers without waiting for someone to open a dashboard. Results come from the public OSV service, so no sign-in is needed to connect it.

What your agent can do with OSV

  • Check whether a package and version has known vulnerabilities
  • Look up a vulnerability by its ID and read out severity and affected versions
  • Check a commit or package URL against the OSV database during a call
  • Send a short summary of findings to a team member after the call

OSV exposes 5 actions. You choose which ones the agent may use and whether each runs during or after the call.

Example calls

Inbound vulnerability question from a developer

  1. Caller

    Hi, I need to know if the lodash version we're running, 4.17.15, has any known problems.

  2. Agent

    Sure. Checking OSV for lodash version 4.17.15 now.

  3. Agent

    It has two known vulnerabilities. The most serious is GHSA-35jh-r3h4-6jhm, a high severity prototype pollution issue. It is fixed in 4.17.21.

  4. Caller

    Great, thanks. Can you send that to our dev channel?

Lookup by vulnerability ID during a support call

  1. Caller

    Our security team flagged CVE-2021-44228. Can you tell me which of our packages it affects?

  2. Agent

    That ID is in the OSV database under the Log4j record. I'll pull the affected package ranges for you.

  3. Agent

    It affects log4j-core from 2.0-beta9 up to 2.15.0, with the fix in 2.15.0 and later. Your team should confirm which version is installed in each service.

  4. Caller

    Got it. Please book a review with Maria for tomorrow at 10 am.

  5. Agent

    Booked for Maria Lopez tomorrow at 10 am. You'll get a confirmation by email.

Follow-up call to a customer about a release

  1. Agent

    Hello, this is Sam from Northwind Software calling for James. Is now a good time?

  2. Caller

    Yes, go ahead.

  3. Agent

    We checked the libraries in your last release against OSV. One dependency, express version 4.17.1, has a medium severity issue fixed in 4.17.3. We recommend upgrading before your next deploy.

  4. Caller

    Thanks, I'll update it this week.

How to connect OSV

  1. 1

    Create your agent

    Sign up to AgentCalls, pick an English or Arabic voice and write what the agent should know and do in plain language.

  2. 2

    Enable OSV

    From Integrations in the dashboard, enable OSV. No sign-in is needed.

  3. 3

    Choose the actions

    In the agent editor, enable the OSV actions the agent may use and set each to run during the call or afterwards. Then test it from your browser.

Questions, answered.

Does the agent check vulnerabilities during the call or after it?

Both. During a call your agent can query OSV live to answer a question about a package, version, commit or vulnerability ID. It can also send a summary to your team after the call.

Do I need an account with OSV to connect it?

No. OSV is a public service, so there is nothing to sign in to. Connect it from the AgentCalls dashboard and your agent can start using it.

Which plan includes this integration?

Integrations are included from the Growth plan. Check the pricing page to compare plans.

Page drafted from the tool's public description and reviewed automatically for accuracy of claims

Put your agent to work with OSV.

Connect in minutes, test from your browser, go live on a number in the US, UK or Gulf. Free to start, no card needed.