Cybrary ForgeCYBRARY / FORGE
Anvil · AI-connected

Practice with the workflow. Perform with the tools.

Anvil brings actual assessment tools into a scoped engagement workspace. Define authorization, run tools through the configured runtime, review original output and manage findings and reporting. Forge training uses emulated assessment workflows.

Book a live demoSafety and scope controls
Authorize, pair, test, review: one governed workflow.
Authorize, pair, test, review: one governed workflow.
See it in action

Follow a finding from command to report

A recorded walkthrough of the real evidence path: scope, approved command, original output and the reviewed finding.

Book a live demo
Evidence walkthrough

From approved command to reviewable finding.

Open →
Anvil AI

Cited answers and evidence-quality checks.

Open →
Integrations

Reporting and remediation hand-offs.

Open →
Pentest training

Emulated engagements, CVSS findings and reports.

Open →
Finding-to-exercise

Turn an approved finding into private team practice, then record the real retest.

Open →
How it works
  1. 01
    Authorize

    Scope and permission are recorded before any testing.

  2. 02
    Test locally

    Your own tools on your own machine, inside the agreed scope.

  3. 03
    Review

    Findings are drafted from evidence and approved by a manager.

  4. 04
    Report

    PDF and Word reports, replay and a signed-off close.

Rehearse the workflow in an emulated environment before the authorized engagement.
Rehearse the workflow in an emulated environment before the authorized engagement.
AI in the workflow

AI that cites evidence and never approves testing

Ask Anvil answers with citations from the engagement and drafts findings from real output. Chat is communication, not authorization.

Capabilities

What you get with Forge

CapabilityCybrary Forge
Recorded scope and authorization Yes
Manager-approved findings Yes
Evidence-cited AI answers Yes
PDF and Word reports Yes
Engagement replay Yes
Finding-to-exercise practice loop Yes

Forge capabilities verified in the product. Competitor documentation varies; absence from their materials is not treated as absence of functionality.

Bring your pentest work into one place.

Follow a finding from command to report, or talk to us about your team's engagements.

See Forge in actionBrowse labs & scenariosTalk to our team

Finding-to-exercise

From a real finding to team practice to a verified fix

When a manager approves an Anvil finding, Forge AI drafts a private practice lab from it. Your team reviews and publishes it, trains on it, and the real retest is recorded against the same finding, so you can see what was found, who practiced and whether the fix held.

A recorded rehearsal: four seats in one Crisis Sim room tick their steps and sign off.

  1. 1. Approved finding

    Only manager-approved findings can become exercises.

  2. 2. Private draft

    Forge AI writes an emulated practice lab from customer-safe details. Hosts, addresses, credentials and commands are stripped first.

  3. 3. Human review

    A person with lab creator rights edits and publishes. It stays private to your company.

  4. 4. Team practice

    People trained, pass rate and time to finish show on the finding.

  5. 5. Real retest

    Fixed, partly fixed or not fixed is recorded with a readiness snapshot. Not fixed? Draft an updated exercise.

  • Built only from manager-approved findings
  • Scrubbed of hosts, addresses, emails, secrets and commands before AI sees it
  • Always private to the finding's company
  • Published only by a person, through the normal completability check
  • Readiness snapshot saved with every retest result
  • Per-engagement summary export (CSV)

Practice results come from an emulated exercise and show readiness, not proof the real system is fixed. Training never authorizes a retest; that still needs its own window and signed rules of engagement.

See the loop in a demo