greydgl--pentestgpt
Gelei Deng
ab5fbb4d90
* first refactor
* feat: dockerized tool with persistent Claude+Codex login + multi-model benchmark
Run the autonomous CTF/pentest tool in Docker with a one-time, persistent login for
BOTH Claude Code and Codex, and add a multi-model benchmark harness.
Backend (multi-model):
- Add `--backend {claude,codex}` to the CTF pipeline. CodexBackend (pentestgpt/core/
backend.py) wraps unified_agent's Codex backend and translates its events into
AgentMessages, so the same pipeline runs on Claude (opus/sonnet) or Codex
(gpt-5.5/gpt-5.4-mini). Wired through config.backend, pipeline stage construction,
and the CLI (+ PENTESTGPT_CODEX_EFFORT; greppable [CODEX_USAGE] under PENTESTGPT_BENCH=1).
Docker tool (tool-only image; the benchmark stays OUTSIDE the image):
- Extend Dockerfile: Codex CLI (@openai/codex) + openai_codex SDK + unified_agent/
pentestgpt_agent/pentestgpt_legacy packages + gobuster/dirb + socat. Add .dockerignore
(keeps creds/benchmark/workspace out of the build context).
- Persistent dual login (the hard part) — asymmetric by token model:
* Claude: `setup-token` -> token stored in the pentestgpt-claude volume; entrypoint
exports CLAUDE_CODE_OAUTH_TOKEN (setup-token does not write .credentials.json; macOS
host creds live in the Keychain and can't be copied).
* Codex: the container does its OWN `codex login` (NOT seeding -- ChatGPT refresh tokens
are single-use, so a shared/copied login 401s on first refresh). The 127.0.0.1:1455
OAuth callback is forwarded into the container via a socat hop (-p 1455:8455).
* scripts/docker-login.sh is idempotent: checks logins live, logs in only the missing one(s).
- docker-compose codex-config volume (+ pinned names); entrypoint token-export + non-blocking
preflight; scripts/docker-auth-status.sh; Make targets (docker-build/login/auth-status/
run/shell/down/nuke).
- Verified end-to-end: one `make docker-login` -> a fresh container reports claude+codex
logged in with live round-trips; the CTF pipeline (Codex) captured a flag against an
isolated fixture and the pentest pipeline ran cleanly; persists across recreation, no re-login.
Benchmark (multi-model, host-side):
- benchmark/pilot/ harness (run_pilot.py + report.py): builds each xbow challenge, discovers
the loopback port, runs the pipeline across the 4 model combos, judges by the baked
FLAG{sha256(UPPER-dir)}, and renders REPORT.md (infra failures excluded from solve rates).
Includes the partial pilot's results (results.jsonl + REPORT.md).
Docs: docs/docker-dev-plan.md (full plan + implementation status); CLAUDE.md and README
docker quickstart; benchmark/pilot/README.md; design-doc roadmap (docs/redesign).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix: fail controller on backend error messages
* fix: allow listing sessions without target
* docs: add docker xbow benchmark report
* fix: infer concrete backend constructor type
* docs: refresh docker benchmark documentation
* feat(benchmark): add pure single-agent baseline + pipeline comparison
Add a "pure single agent" benchmark variant -- one bare `claude -p` /
`codex exec` call per target (no pipeline) -- to quantify what the 3-stage
PentestGPT pipeline buys over an un-orchestrated agent on the xbow targets.
- pentestgpt/prompts/stages.py: ctf_single_agent_{system,task}_prompt -- the
pipeline's shared fragments collapsed into ONE turn, so prompt content is
held constant and the only variable is the multi-stage decomposition.
- benchmark/pilot/run_docker_bench.py: docker-network runner
(--variant single|pipeline). Brings the target up, discovers the container's
internal IP+network (skips DB side-cars/ports), docker-runs the tool image on
that network, and scores the ground-truth flag against the agent's *assistant
text* only (parity with the pipeline's raw streaming). Reads stdout in chunks
to handle >64KB JSON lines. Resumable; --dry-run supported.
- benchmark/pilot/report_comparison.py -> DOCKER_COMPARISON.md: head-to-head
pipeline-vs-single per model on the common non-infra set.
- tests/unit/test_single_agent_prompt.py: prompt-builder coverage.
- docs: README, CLAUDE.md, benchmark README, DOCKER_REPORT updated.
Recorded result (10 medium/hard targets x 4 models, container-to-container,
same baseline image digest 0c4c0f3e..., commit dca0019 image):
Model Pipeline Single
Claude Opus 5/10 7/10 (single +2)
Claude Sonnet 6/10 4/10 (pipeline +2)
Codex gpt-5.5 7/10 7/10 (tie)
Codex gpt-5.4-mini 3/10 4/10 (single +1)
TOTAL 21/40 22/40
Single agent matches the pipeline on solve rate (55% vs 52%) while using
~40% fewer Codex tokens (13.0M vs 21.8M) and solving faster. The pipeline
only clearly helps Claude Sonnet (which times out solo); Opus is better solo.
Full per-challenge grid in DOCKER_COMPARISON.md; raw records in
docker_single_results.jsonl.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(benchmark): add pentestgpt_agent docker harness
* bench: refresh pentestgpt_agent smoke result
* fix(benchmark): make repeat rows variant-aware
* fix(agent): fall back for semantic executor labels
* fix(agent): tolerate executor prose evidence
* fix(benchmark): score accepted framework findings
* bench: append partial framework repeat results
* bench: complete framework repeat sweep
* bench: expose framework executor concurrency
* bench: add extended parallel framework sweep
* checkpoint: preserve working agent and benchmark state
* feat: harden durable agent loop and xbow qualification
* fix: reserve an exploit result turn
* docs: record clean xbow qualification
* build: consume unified-agent from the git wrapper repo
Repoint pentestgpt_agent_new's unified-agent dependency from the local
editable path (../../UnifiedAgentPoC, now renamed and gone) to the pinned
git source PentestGPT-Project/UnifedAgentWrapper@d05d21f. Regenerate uv.lock
and update test_dependency.py to assert the external package is installed
from that VCS URL (not the repo-root vendored copy) at version 0.2.0.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* refactor: make pentestgpt_agent_new the sole framework
Remove the retired ledger-based pentestgpt_agent package (instructor/executor/
judge) and its orphaned unit + smoke tests. The nested pentestgpt_agent_new
project (Supervisor/Executor over a durable SQLite loop, consuming unified-agent
from the git wrapper) is now the single maintained framework.
Repoint the top-level tooling to it:
- pyproject: drop the pentestgpt-agent console script and pentestgpt_agent from
the wheel packages.
- Makefile: lint/format target parent code only; typecheck/check/ci now run the
nested framework's own gate (ruff, format, mypy, pytest) via test-agent-new /
check-agent-new, so `make check` finally covers it; `make run` delegates to the
pentestgpt-agent-new CLI.
- Dockerfile: stop copying the removed package (kept the build working); note the
framework is not baked into the image yet.
- docker container-health test: import the substrate packages that actually ship.
- CLAUDE.md / AGENT.md: describe the new framework, the git-sourced wrapper, and
the deprioritized benchmark/Docker rewire.
The XBOW `--variant framework` path and docker-bench Makefile targets still point
at the old in-image framework and are left as a pending rewire (benchmarks
deprioritized); the naive `--variant single` path is unaffected.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* refactor: rename pentestgpt_agent_new -> pentestgpt_agent
The framework reclaims the clean name now that the old ledger-based package is
gone. Rename the nested project folder, its src package, the distribution
(pentestgpt-agent-new -> pentestgpt-agent) and CLI, and every import/reference in
the package, the umbrella Makefile, the Dockerfile, the docker health test, and
CLAUDE.md / AGENT.md. Regenerate uv.lock. The audit CLI stays pentestgpt-agent-audit;
the git-sourced unified-agent dependency is unchanged. `make check` is green
(108 nested tests). The two historical *_REPORT.md files keep the old name as
dated records.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore: extract benchmark harness to sibling xbow-benchmark repo
Move PentestGPT/benchmark/ out to ../xbow-benchmark (its own repo) to keep this
project clean. The harness was decoupled from the framework code (it scores
container output, never imports pentestgpt_agent/unified_agent), so only
operational ties remain and they now live in the sibling repo.
- Remove benchmark/ and the 4 harness unit tests (relocated + repointed there).
- Strip the docker-bench-*/bench-* targets and their config vars from the
Makefile; keep the tool-image lifecycle (docker-build/login/run/...) and add a
help pointer to `make -C ../xbow-benchmark help`.
The sibling repo mounts this checkout read-only (--source-root ../PentestGPT) and
runs the pentestgpt:latest image built here.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat: harden autonomous framework and runtime integration
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
151 行
4.0 KiB
TOML
151 行
4.0 KiB
TOML
[project]
|
|
name = "pentestgpt"
|
|
version = "1.0.0"
|
|
description = "AI-powered autonomous penetration testing agent - Published at USENIX Security 2024"
|
|
authors = [{ name = "Gelei Deng", email = "GELEI.DENG@ntu.edu.sg" }]
|
|
readme = "README.md"
|
|
license = { text = "MIT" }
|
|
requires-python = ">=3.12,<4.0"
|
|
keywords = [
|
|
"penetration-testing",
|
|
"security",
|
|
"ai",
|
|
"claude",
|
|
"pentest",
|
|
"cybersecurity",
|
|
"ctf",
|
|
"hacking",
|
|
]
|
|
classifiers = [
|
|
"Development Status :: 4 - Beta",
|
|
"Environment :: Console",
|
|
"Intended Audience :: Developers",
|
|
"Intended Audience :: Information Technology",
|
|
"Topic :: Security",
|
|
"License :: OSI Approved :: MIT License",
|
|
"Programming Language :: Python :: 3.12",
|
|
]
|
|
dependencies = [
|
|
"pydantic>=2.5.0",
|
|
"pydantic-settings>=2.1.0",
|
|
"python-dotenv>=1.0.0",
|
|
"langfuse>=2.0.0",
|
|
# Modernized legacy PentestGPT: interactive UI + native multi-provider LLM SDKs.
|
|
"prompt-toolkit>=3.0.0",
|
|
"rich>=13.0.0",
|
|
"loguru>=0.7.0",
|
|
"openai>=1.55.0",
|
|
"anthropic>=0.49.0",
|
|
"google-genai>=1.0.0",
|
|
# Transitional dependencies of the obsolete root unified_agent compatibility copy.
|
|
# The maintained framework resolves unified-agent from UnifedAgentWrapper instead.
|
|
"claude-agent-sdk>=0.2.90",
|
|
"openai-codex>=0.1.0b3",
|
|
"mcp>=1.23.0",
|
|
"pyyaml>=6.0",
|
|
]
|
|
|
|
[project.scripts]
|
|
pentestgpt-legacy = "pentestgpt_legacy.main:main"
|
|
pentestgpt-legacy-connection = "pentestgpt_legacy.test_connection:test_connection"
|
|
|
|
[project.urls]
|
|
Homepage = "https://github.com/GreyDGL/PentestGPT"
|
|
Repository = "https://github.com/GreyDGL/PentestGPT"
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["pentestgpt_legacy", "unified_agent"]
|
|
|
|
# ============================================================================
|
|
# uv Configuration
|
|
# ============================================================================
|
|
|
|
[tool.uv]
|
|
prerelease = "allow"
|
|
dev-dependencies = [
|
|
"ruff>=0.1.0",
|
|
"mypy>=1.7.0",
|
|
"pytest>=7.4.0",
|
|
"pytest-asyncio>=0.21.0",
|
|
"pytest-cov>=4.1.0",
|
|
]
|
|
|
|
# ============================================================================
|
|
# Ruff Configuration (Linter & Formatter)
|
|
# ============================================================================
|
|
|
|
[tool.ruff]
|
|
target-version = "py312"
|
|
line-length = 100
|
|
extend-exclude = [
|
|
".git",
|
|
".mypy_cache",
|
|
".pytest_cache",
|
|
".ruff_cache",
|
|
"__pycache__",
|
|
"build",
|
|
"dist",
|
|
]
|
|
|
|
[tool.ruff.lint]
|
|
select = [
|
|
"E", # pycodestyle errors
|
|
"W", # pycodestyle warnings
|
|
"F", # Pyflakes
|
|
"I", # isort
|
|
"UP", # pyupgrade
|
|
"B", # flake8-bugbear
|
|
"C4", # flake8-comprehensions
|
|
"SIM", # flake8-simplify
|
|
"RUF", # Ruff-specific rules
|
|
]
|
|
|
|
ignore = [
|
|
"E501", # Line too long (handled by formatter)
|
|
]
|
|
|
|
[tool.ruff.format]
|
|
quote-style = "double"
|
|
indent-style = "space"
|
|
|
|
# ============================================================================
|
|
# MyPy Configuration (Type Checking)
|
|
# ============================================================================
|
|
|
|
[tool.mypy]
|
|
python_version = "3.12"
|
|
strict = true
|
|
warn_return_any = true
|
|
warn_unused_configs = true
|
|
disallow_untyped_defs = true
|
|
|
|
# Third-party SDKs without complete type stubs (used by pentestgpt_legacy).
|
|
[[tool.mypy.overrides]]
|
|
module = ["google.genai.*", "google.*"]
|
|
ignore_missing_imports = true
|
|
|
|
# ============================================================================
|
|
# Pytest Configuration
|
|
# ============================================================================
|
|
|
|
[tool.pytest.ini_options]
|
|
minversion = "7.0"
|
|
addopts = [
|
|
"--strict-markers",
|
|
"--strict-config",
|
|
]
|
|
testpaths = ["tests"]
|
|
pythonpath = ["."]
|
|
asyncio_mode = "auto"
|
|
markers = [
|
|
"unit: Unit tests (fast, no external dependencies)",
|
|
"integration: Integration tests (may use mocks)",
|
|
"docker: requires a local Docker daemon and may build or start containers",
|
|
"slow: Slow tests (skip with -m 'not slow')",
|
|
"live: Live smoke tests that require backend auth and may spend tokens",
|
|
]
|