Cybersecurity toolkits · Rank #5
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.
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
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
- DataLocal SQLite storage
Findings stored on your machine in SQLite
- OtherMCP client integration
Use it through MCP (Claude Code, Codex, Cursor, VS Code)
- OtherCLI workflow
from the CLI, or in CI/CD
- OtherMachine oracle verification
machine oracles to verify whether an exploit actually works
- OtherBug bounty scope import
import a program's scope (HackerOne, Bugcrowd, Intigriti, YesWeHack)
- OtherScope enforcement
Scope is enforced, not advisory: wildcards, CIDRs and out-of-scope exclusions
- OtherPlatform-ready submissions
turn each verified finding into a platform-ready submission
- OtherBuilt-in methodology playbook
ptai playbook run bug-bounty-web -i target=acme.com --execute
- OtherBundled vulnerable demo
The demo tests a bundled vulnerable application
- OtherLocal model support
Install and start Ollama, then pull a model with tool-calling support
- OtherSARIF export
Reports and SARIF output for existing engineering workflows
- OtherOpt-in telemetry
Anonymous usage counters are opt-in through ptai telemetry enable
- OtherOut-of-band collaborator
Blind-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.
History
Sep 29, 2026 → Oct 19, 2026. One square per check, colored by maintenance status. Hover for details.
Show as a table
| Date | Maintenance | Dependencies | Commits (90d) |
|---|---|---|---|
| Oct 19, 2026 | Active | Current deps | 36 |
| Oct 12, 2026 | Active | Current deps | 36 |
| Sep 29, 2026 | Active | Current deps | 34 |
Sources
Every claim on this page comes from these public records, checked . Open them to verify.
- Commit history ↗ default branch (main) at the checked commit: pulse, contributors, last commit
- Releases ↗ latest release
- pyproject.toml ↗ declared dependency versions and stack (at commit 85b5509)
- README ↗ quoted features at the checked commit
- PyPI ↗ latest versions of Python packages (each linked in the table above)