Findings & checks · 8 flagged
HIGHLong base64-encoded blob hidden in the skill documentationSS-SKILL-INJECT-B64-PAYLOAD-01 · Prompt injection · benchmarks/results/2026-05-12/juice-shop/ptai-llm/unauthed-findings.json
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
- Decode the base64 string and confirm it is not an instruction directed at the agent.
- Move any legitimate binary or signature data into a dedicated file (
*.sig,SIGNATURES) outside the documentation.
Trace & refs
HIGHLong base64-encoded blob hidden in the skill documentationSS-SKILL-INJECT-B64-PAYLOAD-01 · Prompt injection · benchmarks/results/2026-05-12/juice-shop/ptai-sweep/authed-findings.json
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
- Decode the base64 string and confirm it is not an instruction directed at the agent.
- Move any legitimate binary or signature data into a dedicated file (
*.sig,SIGNATURES) outside the documentation.
Trace & refs
HIGHLong base64-encoded blob hidden in the skill documentationSS-SKILL-INJECT-B64-PAYLOAD-01 · Prompt injection · benchmarks/results/2026-05-12/juice-shop/ptai-sweep/unauthed-findings.json
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
- Decode the base64 string and confirm it is not an instruction directed at the agent.
- Move any legitimate binary or signature data into a dedicated file (
*.sig,SIGNATURES) outside the documentation.
Trace & refs
HIGHLong base64-encoded blob hidden in the skill documentationSS-SKILL-INJECT-B64-PAYLOAD-01 · Prompt injection · benchmarks/results/2026-05-15-juiceshop/2dd29513_findings.json
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
- Decode the base64 string and confirm it is not an instruction directed at the agent.
- Move any legitimate binary or signature data into a dedicated file (
*.sig,SIGNATURES) outside the documentation.
Trace & refs
HIGHLong base64-encoded blob hidden in the skill documentationSS-SKILL-INJECT-B64-PAYLOAD-01 · Prompt injection · benchmarks/results/2026-05-15-juiceshop/c1ae665a_findings.json
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
- Decode the base64 string and confirm it is not an instruction directed at the agent.
- Move any legitimate binary or signature data into a dedicated file (
*.sig,SIGNATURES) outside the documentation.
Trace & refs
HIGH"Ignore previous instructions" command embedded in the skillSS-SKILL-INJECT-IGNORE-01 · Prompt injection · agents/llm_redteam/corpus.yaml×2
The text {match} is the classic direct prompt-injection phrasing. Placed in a skill body that the agent reads as trusted instructions, it tries to make the agent abandon its prior rules and follow whatever comes next — a full system-prompt override.
Show all 2 locations
- Delete the
ignore/disregard/forget … previous instructionssentence. - If this is jailbreak-research or tutorial content, move the example into a clearly fenced, non-instruction block and label it as a quoted sample.
Trace & refs
HIGH"Ignore previous instructions" command embedded in the skillSS-SKILL-INJECT-IGNORE-01 · Prompt injection · docs/ROADMAP.md
The text {match} is the classic direct prompt-injection phrasing. Placed in a skill body that the agent reads as trusted instructions, it tries to make the agent abandon its prior rules and follow whatever comes next — a full system-prompt override.
- Delete the
ignore/disregard/forget … previous instructionssentence. - If this is jailbreak-research or tutorial content, move the example into a clearly fenced, non-instruction block and label it as a quoted sample.
Trace & refs
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
<div align="center">
<img src="assets/transparentbanner.png" alt="pentest-ai" width="640">
<h1>pentest-ai</h1>
Autonomous pentests from one command. Real tools, working PoCs, audit-ready reports.
Website · Install · Docs · Benchmarks · Agents · Discord
</div>
⚠️ Offensive tooling, authorized testing only. By installing you accept the AUP and Terms. Full text in Responsible use ↓
Point ptai at a target. It runs recon, logs in, and ties findings into multi-step attack paths. Every finding comes with a working PoC. The report writes itself.
Runs on your laptop. No cloud, no telemetry.
What's new in 0.15.1 (2026-05-16). Three new flags for pointing ptai at real production targets without breaking the engagement rules.intensity=safeskips probes that mutate server state (no mass-assignment, no stored XSS, no race conditions).respect_rate_limits=truehonors HTTP 429 andRetry-Afterinstead of hammering through them.strict_scope=truerefuses any request whose host doesn't match the engagement target, and turns off redirect-following so a 302 to attacker.com can't pull the scan off-target. All three default off - existing 0.14.x behavior is unchanged unless you opt in. There's also a workingbearerauth flow now: POST your creds, ptai pulls the JWT out of a JSON path you configure, then attaches it to every probe. JWT-style APIs (Juice Shop, crAPI, most modern bug-bounty stacks) actually work. Measured: 63.24% catch rate (43/68 in-scope challenges) on OWASP Juice Shop v19.2.1 withintensity=aggressive+strict_scope=true. See CHANGELOG.
>
Also in 0.14.0 (2026-05-13): 200+ wrapped security tools (wpscan, dalfox, hydra, hashcat, paramspider, ffuf, gobuster, sqlmap, ...) are reachable from Claude Code, Cursor, Codex, and any MCP client vialist_tools,run_tool,plan_tools,ensure_tools_installed. No Anthropic API key required. Pick a tool, install missing ones in one batched prompt, run, get findings.
See it run
<p align="center"> <img src="assets/demo.gif" alt="ptai-via-Claude-Code-MCP scanning OWASP Juice Shop: 17 critical findings, 7 attack chains, 264 detection rules generated" width="900"> </p>
One prompt to Claude Code. The MCP server ran ptai's tools against the target, and Claude streamed findings back into the session. Subscription-driven, no API key.
The scan returned 17 critical, 53 high, 107 total findings, 7 confirmed attack chains, and 264 generated detection rules against a stock OWASP Juice Shop instance. JWT alg:none accepted on 8+ protected endpoints, SQLi auth bypass on /rest/user/login, UNION-based SQLi on /rest/products/search, path-filter bypass via NUL byte, XXE disclosing /etc/passwd, file upload polyglot, mass assignment, password reset bypass. Each one has a working PoC.
Recording is the actual output ofclaude -pagainst a local OWASP Juice Shop withpentest-airegistered as an MCP server. Cast file inassets/realdemo.cast; the time-paced re-render used for the GIF is inassets/realdemo-paced.cast. Findings are real; inter-line timing was reconstructed for watchability sinceclaude -pbuffers and dumps in non-interactive mode. A deterministic synthesized fallback (assets/demo.tape+assets/demo.sh) is kept for reproducible re-renders.
Honesty caveat: Juice Shop is the most-written-about deliberately-vulnerable app on the internet, so LLMs and probe authors both have a head start. Against a novel target the catch rate is whatever the curated probe library actually covers: 60 web probes today, growing each release. The LLM coordinates and reasons about results; it doesn't replace the probes. A private honeypot harness intests/honeypot/measures coverage against bugs we wrote ourselves and is asserted in CI at 10/10 caught (tests/honeypot/test_mcp_honeypot_e2e.py). Numbers there are lower than Juice Shop, and that's the point. We publish both. See the full Juice Shop benchmark vs ZAP / Nuclei / HexStrike.
Install
pip install ptaiPath 1: Drive it from Claude Code (no API key)
If you already pay for Claude Pro / Max / Team, your subscription IS the LLM. Wire ptai in as an MCP server:
claude mcp add pentest-ai -- ptai mcpRestart Claude Code, then ask:
"Run an authenticated pentest against staging.acme.com. Login is at /login, password is in $APP_PASS."
What hits the network: ptai's tools and probes execute locally against your target. Your prompts and the tool output that Claude Code reads go through Anthropic's API, same as any Claude Code session. If you need an air-gapped path, see Path 3 (Ollama / on-prem LLM).
Claude Code drives ptai via these MCP tools (49 of them as of 0.14.0):
list_tools/run_tool: list and invoke any of 200+ wrapped security toolsplan_tools/ensure_tools_installed: get the canonical tool list for an engagement, batched installlist_probes/run_probe: 60 SPA-aware probes for OWASP Top 10 bug classeshttp_request: raw HTTP under a hard scope guard for novel chainsstart_engagement/get_findings/get_attack_chains: the engagement record- plus
test_web_app,test_active_directory,test_cloud,test_api_security, and the rest
Path 2: Other MCP clients (Cursor, VS Code Copilot, Codex, Claude Desktop)
ptai setup --mcpAuto-detects every MCP-compatible client you have installed and writes their config files. Restart the client and the same 49 tools are there.
Path 3: Standalone CLI when you DON'T have an MCP client
If you're using Claude Code, Cursor, Codex, or Claude Desktop, use Path 1 or 2 above and skip this section. No API key needed there.
Path 3 is for CI/CD pipelines, scheduled cron jobs, air-gapped terminals, and users without an MCP client. The standalone CLI has no LLM of its own, so you bring one via env var:
export ANTHROPIC_API_KEY=sk-ant-... # Claude (best results)
# or
export OPENAI_API_KEY=sk-... # OpenAI
# or, fully local, no cloud
export PENTEST_AI_LLM_PROVIDER=ollama # Ollama (default localhost:11434)
# or, any of 300+ models via LiteLLM (OpenRouter, Azure, DeepSeek, Groq, Mistral, ...)
pip install litellm
ptai start https://your-target.comHitting an OpenAI-compatible endpoint (DeepSeek cloud, Groq, Together AI, vLLM, etc.)? Set OPENAI_BASE_URL + PENTEST_AI_MODEL and use the openai provider. Full recipes for every provider - including custom model names, troubleshooting, and the LiteLLM-300+ list - live in docs/llm-providers.md.
#### Spending cap (Path 3 only)
The standalone agent loop drives its own LLM, so runaway loops cost real money. ptai caps spend per engagement at $10 USD by default. A normal Sonnet 4.6 web-app sweep with prompt caching finishes well under that; an Opus 4.7 deep run can blow past it.
Change it via env var (no CLI flag - env var is the only knob):
export PTAI_PRICE_LIMIT=25 # raise to $25
export PTAI_PRICE_LIMIT=0 # unlimited (logs a warning)
unset PTAI_PRICE_LIMIT # back to the $10 defaultIf the cap fires mid-engagement, the engagement is marked aborted_cost_limit and its checkpoint is preserved. Raise the cap and resume from where it stopped:
export PTAI_PRICE_LIMIT=25
ptai resume <engagement_id>Paths 1 and 2 (MCP) don't use this cap - your AI client (Claude Code, Cursor, etc.) handles its own LLM billing.
Installing security tools
ptai wraps 200+ external tools. Three ways to get them on the box:
# 1. Zero-config (recommended). At engagement start, the planner predicts
# which tools the LLM will need and asks ONCE to install the missing
# ones. Decline once and the answer persists in
# ~/.pentest-ai/install-preferences.json.
ptai start https://target.example.com
# 2. Batch install upfront. Skips the engagement-time prompt entirely.
ptai setup --tier core # ~6 essentials, ~30s
ptai setup --tier recommended # + fuzzers, crawlers, password tools, ~5m
ptai setup --tier full # everything, ~30m
# 3. Install specific tools by name.
ptai setup --per-tool wpscan,dalfox,paramspider
ptai setup --wizard # interactive pickerIn non-interactive contexts (PTAI_NON_INTERACTIVE=1 or no TTY) ptai uses what's on PATH and logs (rather than prompts) for anything missing.
<details> <summary><strong>Other paths</strong>: REST API, MCP composition, HITL teleoperation, cloud workspace, public benchmarks</summary>
HTTP REST API (for dashboards and integrations)
pip install ptai[api]
ptai serve --port 8888Endpoints: /health, /version, /agents, /tools, /engagements (list, detail, findings, chains, detection rules, SARIF export). Write endpoints (POST /engagements, POST /engagements/{id}/abort) require Authorization: Bearer $PENTEST_AI_API_TOKEN. Live event stream at WS /engagements/{id}/stream.
Load other MCP servers as tool sources
Compose with hexstrike or any other MCP-compatible security server. Edit ~/.pentest-ai/mcp_servers.json:
{
"servers": [
{"name": "hexstrike", "command": "python3 hexstrike_mcp.py", "transport": "stdio"}
]
}Take over mid-run (HITL teleoperation)
While an engagement is running, press Ctrl+C twice within 600ms to pause the orchestrator and drop into a REPL: step, inspect findings, inject <instruction>, skip, resume, abort. Current LLMs aren't fully autonomous. The operator owns the call when it matters.
Public benchmarks
Reproducible solve-rate measurements live in benchmarks/:
./benchmarks/scripts/run_all.sh # writes JSON per run + RESULTS.mdSpec, harness, results all in git. The full Juice Shop comparison vs ZAP / Nuclei / HexStrike is at docs/benchmarks/juice-shop.md. No "98.7% detection rate" claims you can't audit.
Cloud workspace (Pro / Team / Enterprise)
The CLI is free forever and stores everything locally. If you want engagement history, branded client-ready PDF reports, and team collaboration, link the CLI to an app.pentestai.xyz workspace:
# Sign up, then Dashboard -> API Keys -> Generate -> copy ptai_...
ptai auth login # paste the key (hidden prompt)
ptai auth status # confirm link
# or use an env var for CI:
export PENTESTAI_API_KEY=ptai_...ptai start auto-syncs findings to your cloud workspace when authed. No cloud = no calls; integration is silently off unless you log in.
No LLM at all (interactive launcher)
ptai menuNumeric category navigation, search (/term), tag filtering (t web), keyword-based recommendation. Real engagements still go through ptai start with full scope confirmation.
</details>
Why it's different
| 🤖 LLM-coordinated, not LLM-dependent | Seventeen agents cover recon, web, API, AD, cloud, mobile, wireless, browser, credentials, privesc, vuln scan, chaining, PoC, detection, report, social engineering, and LLM red team. The LLM runs the phase loop and reasons about results; bug detection is in the curated deterministic probe library. Set no API key and the same probes still run. The LLM coordinates; it doesn't scan. |
| 🔓 No API key on the MCP path | Claude Code / Cursor / Codex users drive ptai through MCP using their existing subscription. 200+ tool wrappers and 60 probes are LLM-callable without an Anthropic key. The standalone CLI (ptai start --agent-mode) is where the API key matters; that's the Codex-without-MCP, CI, and air-gapped paths. |
| 🔐 It logs in | Most scanners die at the login page. This one holds a session, refreshes credentials when they expire, and every downstream tool inherits the cookie. Auth profiles store references (env vars, op://, Vault paths, AWS Secrets Manager ARNs), never the value. |
| 🧪 Every finding is proven | A non-destructive proof of concept runs against the target. No more triaging 40 maybes from a noisy scanner. |
| ⚡ CI-native | GitHub Action, severity gates, SARIF output, PR comments. Drop it into your workflow file and it runs on the next PR. |
| 💾 Runs on your laptop | MIT licensed, no cloud calls. Runs offline with Ollama. Findings stay on your disk. |
How it works
┌─────────────────────────────────────────────────────────────┐
│ ptai start <target> │
└─────────────────────────────────────────────────────────────┘
│
┌──────────────────┼──────────────────┐
▼ ▼ ▼
┌────────┐ ┌────────┐ ┌─────────┐
│ recon │ -> │ auth │ -> │ web │
└────────┘ └────────┘ └─────────┘
│
┌────────────────────────────────────┤
▼ ▼
┌────────┐ ┌─────────┐
│ ad │ ┌──────────────────┐ │ cloud │
└────────┘ │ Findings DB │ └─────────┘
│ │ (sqlite + evidence)│ │
└───────▶│ scope-guarded │◀──────┘
│ deduplicated │
└──────────────────┘
│
┌────────────┼────────────┐
▼ ▼ ▼
┌──────┐ ┌─────────┐ ┌──────────┐
│chain │ │validate │ │ detect │
└──────┘ └─────────┘ └──────────┘
│
▼
┌──────────┐
│ report │ md · html · pdf · SARIF · JUnit
└──────────┘Each agent runs with an LLM when you've set a key, or as a deterministic tool loop when you haven't. Either way the phase order is the same.
Agents
| Agent | Phase | Does |
|---|---|---|
recon | 1 | Port scan, DNS and subdomain enum, service fingerprinting |
web | 2 | Authenticated OWASP Testing Guide v4 pass |
api_security | 2 | OpenAPI/GraphQL/REST surface analysis, OWASP API Top 10 |
browser | 2 | Playwright-driven DOM analysis, XHR capture, security-header grading |
ad | 3 | AD enum, Kerberoasting, BloodHound pathfinding, delegation abuse |
cloud | 4 | AWS, Azure, GCP IAM, misconfig, K8s RBAC, serverless |
credential_tester | 4 | Password spraying, credential stuffing, MFA bypass checks |
privesc | 5 | Local and lateral privilege-escalation advice from collected context |
vuln_scanner | 5 | Cross-cutting vuln aggregation against the findings DB |
exploit_chain | 6 | Correlates findings into multi-step attack paths |
poc_validator | 7 | Non-destructive proof of concept per finding |
detection | 8 | Sigma, SPL, KQL rules for the blue team |
report | 9 | Markdown, HTML, PDF, SARIF, JUnit, compliance maps |
llm_redteam | opt | OWASP LLM Top 10 probes |
social_engineer | opt | Phishing corpus and pretext generation |
mobile | opt | Android/iOS static + dynamic checks |
wireless | opt | Wireless reconnaissance and handshake capture |
Playbooks
Your methodology as a file. Checked into git. Shared with your team.
name: internal-ad-pentest
inputs:
domain: { required: true, prompt: "AD domain" }
dc_ip: { required: true, prompt: "DC IP" }
phases:
- id: recon
tools: [nmap, masscan]
- id: ad-enum
depends_on: [recon]
condition: "any_finding(type='open_port', port=445)"
tools: [enum4linux, ldapsearch, bloodhound-python]
- id: kerberoast
requires_finding: { type: ad_user_enumerated }
tools: [impacket-getuserspns]
llm_decide: true # let the LLM skip if context says uselessptai playbook list # show installed playbooks
ptai playbook show web-app-quick # preview before running
ptai playbook run ./my-ad.yaml # executeFive playbooks ship built-in. A community catalog is coming.
Drop it into your CI
# .github/workflows/security.yml
name: Security scan
on: [pull_request]
jobs:
ptai:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- run: pip install ptai
- run: |
ptai start ${{ vars.STAGING_URL }} \
--ci \
--fail-on high \
--sarif pentest.sarif
env:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
- uses: github/codeql-action/upload-sarif@v3
if: always()
with:
sarif_file: pentest.sarifFindings post as a PR comment, SARIF uploads to GitHub Code Scanning, and the build fails on gated severity. GitLab CI and Jenkins templates plus advanced options (auth profiles in CI, cost gates, scope files) -> docs/ci-cd.md.
Benchmarks
ptai's design is purpose-built for SPA pentesting with curated probe coverage. On OWASP Juice Shop, the published 4-tool matrix showed:
| Tool | Findings | Critical+High | OWASP Top 10 buckets | FP rate |
|---|---|---|---|---|
| ptai 0.13.0 | 88 | 46 | 5 | 0% |
| ZAP 2.17.0 | 593 | 0 | 1 | 47% |
| Nuclei 3.8.0 | 1 | 0 | 1 | 0% |
| HexStrike v6.0 | 11 | 0 | 1 | - |
n=1 single-rater, single-shot. Methodology + raw artifacts in benchmarks/results/2026-05-12/juice-shop/. The honest read: ptai is better at SPA web pentests with curated probe coverage. HexStrike is broader (cloud, binary, CTF) and likely beats ptai on traditional crawlable surfaces like WordPress. v5 will widen the comparison.
Recent research context: fully autonomous LLM-pentest agents finish 21-31% of tasks end-to-end; human-assisted setups reach 64% (ARTEMIS, DARPA AICC Atlantis, xOffense). ptai is built for the human-assisted regime: the LLM reasons about results, the curated probes detect, and Ctrl+C twice lets the operator take over.
vs the field
ptai | Hexstrike | ZAP | Nuclei | Burp Pro | PentestGPT | |
|---|---|---|---|---|---|---|
| LLM-driven via MCP (no API key) | ✓ | ✓ | ||||
| LLM-synthesized HTTP under scope guard | ✓ | partial | ||||
| Authenticated scanning via MCP | ✓ | partial | partial | raw HTTP | ✓ | |
| Exploit chaining | ✓ | partial | partial | |||
| Non-destructive PoC validation | ✓ | partial | ||||
| Stored injection chains (POST -> GET verify) | ✓ | manual | partial | manual | ||
| Curated probes (specialised, not template-driven) | 60 | tool-wrapper-driven | rule-driven | 8000+ templates | manual + scan | - |
| Wrapped CLI security tools | 200+ | 150+ | - | - | - | - |
| Tool install wizard | core/recommended/full + per-tool | - | n/a | n/a | n/a | - |
| Smart install at engagement start | ✓ | |||||
| CI-native (SARIF + severity gates) | ✓ | partial | partial | partial | ||
| LLM red team probes | ✓ | |||||
| YAML playbooks | ✓ | templates | ||||
| License | MIT | MIT | Apache-2.0 | MIT | commercial | MIT |
What's inside
- 17 agents across recon, web, API security, AD, cloud, mobile, wireless, browser, credential testing, privilege escalation, vuln scanning, exploit chaining, PoC validation, detection, reporting, LLM red team, social engineering
- 60 curated web probes covering OWASP Top 10 + API Top 10
- 200+ tool wrappers with auto-install: nmap, masscan, nuclei, ffuf, sqlmap, gobuster, wapiti, nikto, dalfox, xsstrike, wpscan, hydra, hashcat, enum4linux, bloodhound-python, the impacket suite, trufflehog, gitleaks, kube-hunter, trivy, prowler, scout-suite, and more
- 4000+ Nuclei templates integrated for atomic vulnerability detection
- 49 MCP tools for LLM-driven engagements, including the 0.14.0 additions (
plan_tools,ensure_tools_installed) that let the outer LLM batch-install tools without an Anthropic API key - 300+ LLM models via the LiteLLM provider (Anthropic, OpenAI, Ollama direct; Azure, OpenRouter, DeepSeek, Groq, Mistral, Together AI, Bedrock, Vertex AI, Cohere via LiteLLM)
- HTTP REST API + WebSocket surface (
ptai serve) for non-MCP integrations - Local web dashboard with live engagement view, findings table, attack chain visualization, SARIF export
- Browser automation agent with screenshot capture, DOM analysis, network capture, security header grading (Playwright-driven)
- Human-In-The-Loop teleoperation (Ctrl+C twice to take over an engagement mid-run)
- MCP client capability to load external MCP servers as tool sources
- Public reproducible benchmark harness in
benchmarks/. Numbers, code, raw artifacts, all in git. - 6 output formats: Markdown, HTML, PDF, SARIF 2.1.0, JUnit XML, compliance mappings (OWASP, CWE, CVE, CVSS v3.1)
- 1,000+ tests with CI on Python 3.10, 3.11, 3.12, 3.13
- MIT licensed, 100% yours
Who uses it for what
AppSec teams. Wire ptai into your CI. Every PR against staging gets an authenticated scan. The build fails on high-severity findings. The fix -> retest -> confirm loop runs on its own.
Consultants. Set up a week-long engagement, point ptai at the target list, and spend your time on the parts that need a human: analyzing findings, picking chains to demonstrate, talking to the client. The report writes itself.
Bug bounty hunters. Run it over breakfast. Come back to a list of validated findings with PoCs ready to paste into HackerOne.
Red teamers. Encode your AD methodology as a YAML playbook. Every new engagement runs it. Same methodology, shared across the team.
Claude Code / Cursor / Codex users. Add ptai as an MCP server. Ask your assistant to run a scan in plain English. Your existing subscription pays for the LLM; ptai supplies the tools.
Developers shipping AI features. Enable --enable-llm-redteam against your chatbot. Get an OWASP LLM Top 10 report in minutes.
Responsible use
pentest-ai is offensive security tooling. It executes real network and host operations against the targets you specify. You are solely responsible for ensuring you have explicit, written authorization to test every target.
By installing or running ptai you agree to the Acceptable Use Policy and the Terms of Service. Testing systems you do not own without written authorization may violate the Computer Fraud and Abuse Act, the Computer Misuse Act 1990, GDPR Article 32, and equivalents in your jurisdiction. Misuse is your sole responsibility.
First-run prompts you to confirm AUP acceptance and persists the choice to ~/.pentest-ai/aup-consent.txt. Set PENTEST_AI_AUP_ACCEPTED=1 in CI to bypass the prompt non-interactively.
On startup ptai loads a scope file. Out-of-scope hosts are refused at tool-invocation time. PoCs are non-destructive by default. Rate limits kick in automatically in stealth mode. Don't be that person.
Out-of-band callbacks (OAST) - privacy
ptai detects blind vulnerability classes (blind SSRF, blind SQLi, blind XXE, blind stored XSS, SSTI, Log4Shell) by emitting payloads that, when fired server-side, ring an out-of-band collaborator. By default, callbacks route to ProjectDiscovery's public oast.fun infrastructure.
What lands on the collaborator and who can read it. Each engagement generates a fresh RSA-2048 keypair in your local ptai process. Interaction payloads (raw HTTP requests, DNS queries, SMTP envelopes received by the collaborator) are AES-CTR-256 encrypted at rest server-side, with the AES key wrapped in RSA-OAEP-SHA256 using your engagement's public key. Only the holder of the matching private key - your local `ptai` process - can decrypt them. ProjectDiscovery (or whoever runs the collaborator) cannot read interaction contents. However, metadata is server-visible: the fact that an interaction happened, source IP of the calling target, timestamp, and protocol.
When to self-host. PortSwigger explicitly forbids public-Burp-Collaborator use in their bug bounty rules of engagement, and large enterprise programs (Meta, Apple, finance) increasingly require that callback infrastructure terminate on tester-controlled hosts. For paid engagements, run your own Interactsh server (Apache-2.0, single Go binary) and point ptai at it:
ptai start http://target --oast-server https://oast.example.com --oast-token <T>To disable OAST entirely:
ptai start http://target --no-oastBlind-vuln classes will not be detected when OAST is off; in-band detection paths (size delta / SQL error markers / metadata signatures / time-based) still run.
Ecosystem
| Repo | What |
|---|---|
| pentest-ai | This repo. The CLI and MCP server. Python product. |
| pentest-ai-agents | Standalone Claude Code subagent markdown files. Optional, runs without this CLI. |
Need shared workspaces, branded PDF reports, SSO, or a managed engagement? The website has Pro / Team / Enterprise dashboards and a one-shot Launch Engagement option. The OSS tool stays OSS, free forever.
Community
- Discord: join the server. Chat, get help, share findings, lurk.
- Questions, ideas, feedback: GitHub Discussions
- Bug reports: GitHub Issues
- Show and tell: post the wildest finding
ptaigave you in Show and tell
FAQ
Do I need an API key? No on the MCP path. If you drive ptai from Claude Code, Cursor, Codex, or Claude Desktop, your existing subscription is the LLM. You only need a key on the standalone CLI (Path 3), and even there you can run fully local with Ollama. See Install.
Is it really autonomous, or do I babysit it? You stay in the loop. ptai is LLM-coordinated, not autonomous - the curated probes do the detection, the LLM reasons about results, and you own the call. Press Ctrl+C twice mid-run to take over. Fully-autonomous LLM agents finish 21-31% of pentest tasks end to end; human-assisted setups reach 64%, and ptai is built for that second regime.
Is it safe to point at production? Only with written authorization, and only with the guardrails on: intensity=safe skips state-mutating probes, respect_rate_limits honors 429 / Retry-After, and strict_scope refuses off-host requests and stops following redirects. All three default off, so turn them on. See Responsible use.
Why is the Juice Shop number high but the honeypot lower? Juice Shop is the most-documented vulnerable app on the internet, so the LLM and the probe authors both have a head start. The private honeypot measures bugs we wrote ourselves, so its number is lower - and that lower number is the honest signal. We publish both. See Benchmarks.
Does it phone home? No telemetry, and findings stay on your disk. On the MCP path your prompts and the tool output your AI client reads go through that client's API, the same as any session. Blind-vuln detection (OAST) sends callbacks to public oast.fun by default - the contents are encrypted to a local keypair, but the fact a callback happened plus source IP and timestamp are visible to whoever runs the collaborator. Self-host Interactsh or run with --no-oast to avoid that. See Responsible use.
What does it cost to run? On the MCP path, nothing beyond your AI subscription, which handles its own billing. On the standalone CLI, ptai caps spend at $10 per engagement by default; change it with PTAI_PRICE_LIMIT. See Install.
How is this different from just using Claude or PentestGPT? A curated deterministic probe library finds the bugs; the LLM runs the phase loop and reasons about results, it doesn't scan. That is why findings reproduce and ship with a working PoC instead of an LLM guess. See Why it's different and vs the field.
Star history
<a href="https://star-history.com/#0xSteph/pentest-ai&Date"> <img src="https://api.star-history.com/svg?repos=0xSteph/pentest-ai&type=Date" alt="Star history chart" width="600"> </a>
License
MIT. Do whatever you want with it.
<div align="center">
If `ptai` saved you a Sunday, [star the repo](https://github.com/0xSteph/pentest-ai). It's the only payment I ask for.
</div>