greydgl--pentestgpt
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>
165 行
6.0 KiB
Python
165 行
6.0 KiB
Python
"""Tests for flag detection patterns.
|
|
|
|
Unit tests for the flag detection regex patterns used in PentestAgent.
|
|
"""
|
|
|
|
import re
|
|
|
|
import pytest
|
|
|
|
# Flag patterns retained for compatibility with historical CTF scoring behavior.
|
|
FLAG_PATTERNS = [
|
|
r"flag\{[^\}]+\}", # flag{...}
|
|
r"FLAG\{[^\}]+\}", # FLAG{...}
|
|
r"HTB\{[^\}]+\}", # HTB{...}
|
|
r"CTF\{[^\}]+\}", # CTF{...}
|
|
r"[A-Za-z0-9_]+\{[^\}]+\}", # Generic CTF format
|
|
r"\b[a-f0-9]{32}\b", # 32-char hex (HTB user/root flags)
|
|
]
|
|
|
|
|
|
def detect_flags(text: str) -> list[str]:
|
|
"""Detect potential flags in text using regex patterns."""
|
|
flags = []
|
|
for pattern in FLAG_PATTERNS:
|
|
matches = re.finditer(pattern, text, re.IGNORECASE)
|
|
for match in matches:
|
|
flag = match.group(0)
|
|
if flag not in flags:
|
|
flags.append(flag)
|
|
return flags
|
|
|
|
|
|
@pytest.mark.unit
|
|
class TestFlagDetection:
|
|
"""Tests for flag detection patterns."""
|
|
|
|
def test_detect_flag_lowercase(self):
|
|
"""Test detecting lowercase flag{...} pattern."""
|
|
text = "The flag is flag{s3cr3t_p4ssw0rd}"
|
|
flags = detect_flags(text)
|
|
assert "flag{s3cr3t_p4ssw0rd}" in flags
|
|
|
|
def test_detect_flag_uppercase(self):
|
|
"""Test detecting uppercase FLAG{...} pattern."""
|
|
text = "Found: FLAG{ADMIN_ACCESS}"
|
|
flags = detect_flags(text)
|
|
assert "FLAG{ADMIN_ACCESS}" in flags
|
|
|
|
def test_detect_htb_flag(self):
|
|
"""Test detecting HTB{...} pattern."""
|
|
text = "HackTheBox flag: HTB{h4ck_th3_pl4n3t}"
|
|
flags = detect_flags(text)
|
|
assert "HTB{h4ck_th3_pl4n3t}" in flags
|
|
|
|
def test_detect_ctf_flag(self):
|
|
"""Test detecting CTF{...} pattern."""
|
|
text = "Capture the flag: CTF{y0u_w1n}"
|
|
flags = detect_flags(text)
|
|
assert "CTF{y0u_w1n}" in flags
|
|
|
|
def test_detect_custom_ctf_format(self):
|
|
"""Test detecting custom CTF format like picoCTF{...}."""
|
|
text = "Here is the flag: picoCTF{custom_flag_here}"
|
|
flags = detect_flags(text)
|
|
assert "picoCTF{custom_flag_here}" in flags
|
|
|
|
def test_detect_32_char_hex(self):
|
|
"""Test detecting 32-character hex flags (HTB user/root)."""
|
|
text = "User flag: 0123456789abcdef0123456789abcdef"
|
|
flags = detect_flags(text)
|
|
assert "0123456789abcdef0123456789abcdef" in flags
|
|
|
|
def test_detect_32_char_hex_mixed_case(self):
|
|
"""Test detecting 32-char hex with mixed case."""
|
|
text = "Root flag: aBcDeF0123456789aBcDeF0123456789"
|
|
flags = detect_flags(text)
|
|
# The pattern should match (case insensitive)
|
|
assert any("abcdef0123456789abcdef0123456789" in f.lower() for f in flags)
|
|
|
|
def test_detect_multiple_flags(self):
|
|
"""Test detecting multiple flags in one text."""
|
|
text = """
|
|
Found these flags:
|
|
- flag{first_flag}
|
|
- HTB{second_flag}
|
|
- 0123456789abcdef0123456789abcdef
|
|
"""
|
|
flags = detect_flags(text)
|
|
assert len(flags) >= 3
|
|
assert "flag{first_flag}" in flags
|
|
assert "HTB{second_flag}" in flags
|
|
assert "0123456789abcdef0123456789abcdef" in flags
|
|
|
|
def test_no_false_positives_short_hex(self):
|
|
"""Test that short hex strings are not detected as flags."""
|
|
text = "Hash: abc123 and ID: 12345678"
|
|
flags = detect_flags(text)
|
|
# Should not detect short hex strings
|
|
assert "abc123" not in flags
|
|
assert "12345678" not in flags
|
|
|
|
def test_no_false_positives_31_char_hex(self):
|
|
"""Test that 31-char hex strings are not detected as flags."""
|
|
text = "Almost: 0123456789abcdef0123456789abcde" # 31 chars
|
|
flags = detect_flags(text)
|
|
# Should not include 31-char strings
|
|
assert not any(len(f) == 31 and f.isalnum() for f in flags)
|
|
|
|
def test_no_false_positives_33_char_hex(self):
|
|
"""Test that 33-char hex strings are not detected as flags."""
|
|
text = "Too long: 0123456789abcdef0123456789abcdefa" # 33 chars
|
|
flags = detect_flags(text)
|
|
# The pattern should not match the full 33-char string
|
|
# (may match first 32 chars depending on pattern)
|
|
assert "0123456789abcdef0123456789abcdefa" not in flags
|
|
|
|
def test_flag_with_special_content(self):
|
|
"""Test detecting flags with special characters in content."""
|
|
text = "flag{c0mp13x_fl4g_w1th_und3rsc0r3s}"
|
|
flags = detect_flags(text)
|
|
assert "flag{c0mp13x_fl4g_w1th_und3rsc0r3s}" in flags
|
|
|
|
def test_flag_in_json_context(self):
|
|
"""Test detecting flags in JSON-like output."""
|
|
text = '{"result": "success", "flag": "flag{json_flag_123}"}'
|
|
flags = detect_flags(text)
|
|
assert "flag{json_flag_123}" in flags
|
|
|
|
def test_flag_in_command_output(self):
|
|
"""Test detecting flags in command output context."""
|
|
text = """
|
|
cat /root/root.txt
|
|
HTB{r00t_4cc3ss_gr4nt3d}
|
|
"""
|
|
flags = detect_flags(text)
|
|
assert "HTB{r00t_4cc3ss_gr4nt3d}" in flags
|
|
|
|
def test_empty_string(self):
|
|
"""Test that empty string returns no flags."""
|
|
flags = detect_flags("")
|
|
assert flags == []
|
|
|
|
def test_no_flags(self):
|
|
"""Test text with no flags returns empty list."""
|
|
text = "This is just regular text without any flags."
|
|
flags = detect_flags(text)
|
|
# May detect some false positives with generic pattern, but
|
|
# main flag formats should not match
|
|
assert not any(f.startswith(("flag{", "FLAG{", "HTB{", "CTF{")) for f in flags)
|
|
|
|
def test_flag_case_insensitive(self):
|
|
"""Test that flag detection is case insensitive."""
|
|
text = "FlaG{MiXeD_CaSe}"
|
|
flags = detect_flags(text)
|
|
# Should detect the flag
|
|
assert len(flags) >= 1
|
|
|
|
def test_duplicate_flags_not_repeated(self):
|
|
"""Test that duplicate flags are not returned multiple times."""
|
|
text = "flag{duplicate} and again flag{duplicate}"
|
|
flags = detect_flags(text)
|
|
# Count occurrences of the duplicate flag
|
|
count = flags.count("flag{duplicate}")
|
|
assert count == 1
|