Cybersecurity toolkits · Rank #5

A

pentest-ai

Grade A: derived only from the two verdicts below. How grades work

Open-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a proof capsule you can replay yourself.

ActiveCurrent depsFree

Why this verdict

How we check →
  • 36 commits by 1 contributor in the last 90 days (2 in the last 30). receipt ↗
  • Latest release v1.5.0, 11 days ago. receipt ↗
  • On current major: Pydantic. receipt ↗

Snapshot: commit 85b5509 on main, checked 2026-10-19 06:20 UTC. Receipts link to files at this exact commit.

Dependency freshness

PackageDeclaredLatestStatus
Pydantic pydantic2.0.02.14.1Current

Declared = lowest version the kit's dependency file (package.json, pyproject.toml or requirements.txt) allows. Latest = the npm "latest" tag or the newest PyPI release. TypeScript, the Stripe SDK, FastAPI and other 0.x packages are shown but not counted in the verdict.

What's in the stack

API layer
Pydantic

Detected from declared dependencies. A listed package means it's installed, not necessarily fully wired up.

What the README says you get

  • Data
    Local SQLite storageFindings stored on your machine in SQLite
  • Other
    MCP client integrationUse it through MCP (Claude Code, Codex, Cursor, VS Code)
  • Other
    CLI workflowfrom the CLI, or in CI/CD
  • Other
    Machine oracle verificationmachine oracles to verify whether an exploit actually works
  • Other
    Bug bounty scope importimport a program's scope (HackerOne, Bugcrowd, Intigriti, YesWeHack)
  • Other
    Scope enforcementScope is enforced, not advisory: wildcards, CIDRs and out-of-scope exclusions
  • Other
    Platform-ready submissionsturn each verified finding into a platform-ready submission
  • Other
    Built-in methodology playbookptai playbook run bug-bounty-web -i target=acme.com --execute
  • Other
    Bundled vulnerable demoThe demo tests a bundled vulnerable application
  • Other
    Local model supportInstall and start Ollama, then pull a model with tool-calling support
  • Other
    SARIF exportReports and SARIF output for existing engineering workflows
  • Other
    Opt-in telemetryAnonymous usage counters are opt-in through ptai telemetry enable
  • Other
    Out-of-band collaboratorBlind-vulnerability checks can use an external out-of-band collaborator

Extracted from the kit's README by a local AI model (deepseek-flash) on Oct 12, 2026. Every item is checked against an exact README quote; 1 unverifiable item was discarded. A README claim is the maker's description, not something we tested.

Watch pentest-ai

Get told if it goes dormant, gets archived, falls further behind on a core dependency, or changes its license or price.

You'll get a confirmation email first. One click to unsubscribe. Watch as many kits as you like.

RSS feed for pentest-ai · all changes

History

Sep 29, 2026 → Oct 19, 2026. One square per check, colored by maintenance status. Hover for details.

Show as a table
DateMaintenanceDependenciesCommits (90d)
Oct 19, 2026ActiveCurrent deps36
Oct 12, 2026ActiveCurrent deps36
Sep 29, 2026ActiveCurrent deps34

Sources

Every claim on this page comes from these public records, checked . Open them to verify.

Maintainer? Add the badge

It updates automatically every time we refresh the evidence. Clicking it opens this page.

kitproof badge for pentest-ai
[![kitproof](https://kitproof.dev/badge/pentest-ai.svg)](https://kitproof.dev/kits/pentest-ai/)