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>
108 行
4.2 KiB
JSON
108 行
4.2 KiB
JSON
{
|
|
"version": 1,
|
|
"skills": {
|
|
"ask-matt": {
|
|
"source": "mattpocock/skills",
|
|
"sourceType": "github",
|
|
"skillPath": "skills/engineering/ask-matt/SKILL.md",
|
|
"computedHash": "f3ac3351e2a242ce2591e4f8475424d58f62db3f5786332b78f330b15312d1e0"
|
|
},
|
|
"codebase-design": {
|
|
"source": "mattpocock/skills",
|
|
"sourceType": "github",
|
|
"skillPath": "skills/engineering/codebase-design/SKILL.md",
|
|
"computedHash": "2426dc4accf1a85dedfb560edb3a877ec8828b7375ea08c970df2b6c900a2a22"
|
|
},
|
|
"diagnosing-bugs": {
|
|
"source": "mattpocock/skills",
|
|
"sourceType": "github",
|
|
"skillPath": "skills/engineering/diagnosing-bugs/SKILL.md",
|
|
"computedHash": "1a993ce9b2aaa653ee441c8d7efb7f27de03493c722be6dfb8137bcb8db1bc72"
|
|
},
|
|
"domain-modeling": {
|
|
"source": "mattpocock/skills",
|
|
"sourceType": "github",
|
|
"skillPath": "skills/engineering/domain-modeling/SKILL.md",
|
|
"computedHash": "67343881f5def98487d56243155716110afbcbf22ec92421c882d532b941cb17"
|
|
},
|
|
"grill-me": {
|
|
"source": "mattpocock/skills",
|
|
"sourceType": "github",
|
|
"skillPath": "skills/productivity/grill-me/SKILL.md",
|
|
"computedHash": "f321507f77702a54af1db66549ec1685fc625390d06c57d7949cdcda8eb1b5c7"
|
|
},
|
|
"grill-with-docs": {
|
|
"source": "mattpocock/skills",
|
|
"sourceType": "github",
|
|
"skillPath": "skills/engineering/grill-with-docs/SKILL.md",
|
|
"computedHash": "e7ef25bbee50cda2eb7b3a8ef541db0a0396dad7d369f7d14fb610671dd1864b"
|
|
},
|
|
"grilling": {
|
|
"source": "mattpocock/skills",
|
|
"sourceType": "github",
|
|
"skillPath": "skills/productivity/grilling/SKILL.md",
|
|
"computedHash": "ef685a6fa0bbe73b05bbd8dc1ec97258191587f07c6aa7dbc9006675ceb8f90f"
|
|
},
|
|
"handoff": {
|
|
"source": "mattpocock/skills",
|
|
"sourceType": "github",
|
|
"skillPath": "skills/productivity/handoff/SKILL.md",
|
|
"computedHash": "5d0f81e38abe6b984e1feaa731927de5291d040982106ac513cf54ec240e00ec"
|
|
},
|
|
"improve-codebase-architecture": {
|
|
"source": "mattpocock/skills",
|
|
"sourceType": "github",
|
|
"skillPath": "skills/engineering/improve-codebase-architecture/SKILL.md",
|
|
"computedHash": "8bf292143ca93b00276a0de0fc5f84f2381f4690c5b0d32e99fa283a072f392f"
|
|
},
|
|
"prototype": {
|
|
"source": "mattpocock/skills",
|
|
"sourceType": "github",
|
|
"skillPath": "skills/engineering/prototype/SKILL.md",
|
|
"computedHash": "40ff56e36bb13b5a9a16903efd6c78a02690ba430e10a8d1a65559100b77f475"
|
|
},
|
|
"setup-matt-pocock-skills": {
|
|
"source": "mattpocock/skills",
|
|
"sourceType": "github",
|
|
"skillPath": "skills/engineering/setup-matt-pocock-skills/SKILL.md",
|
|
"computedHash": "400da4521ed701c99e8824ae7b71c7859632ee91481b3715890036cf8aec6857"
|
|
},
|
|
"tdd": {
|
|
"source": "mattpocock/skills",
|
|
"sourceType": "github",
|
|
"skillPath": "skills/engineering/tdd/SKILL.md",
|
|
"computedHash": "d5ca5c8ae0615f343f1cfd71591f4a586046d77b1f36e8d67b8f643bad51043e"
|
|
},
|
|
"teach": {
|
|
"source": "mattpocock/skills",
|
|
"sourceType": "github",
|
|
"skillPath": "skills/productivity/teach/SKILL.md",
|
|
"computedHash": "9cd31ea42b40915ea5fd3949ed229b217d1dfad07dd93d9b0db771dcdd6a6c8a"
|
|
},
|
|
"to-issues": {
|
|
"source": "mattpocock/skills",
|
|
"sourceType": "github",
|
|
"skillPath": "skills/engineering/to-issues/SKILL.md",
|
|
"computedHash": "4e2a11d35f018490d42a79234432f779d7131b9920373ef24cfbc68229bfef6c"
|
|
},
|
|
"to-prd": {
|
|
"source": "mattpocock/skills",
|
|
"sourceType": "github",
|
|
"skillPath": "skills/engineering/to-prd/SKILL.md",
|
|
"computedHash": "5a733e19d825f22e83de52e68b8840c9fd2fa7501282277a122c1aa28a922059"
|
|
},
|
|
"triage": {
|
|
"source": "mattpocock/skills",
|
|
"sourceType": "github",
|
|
"skillPath": "skills/engineering/triage/SKILL.md",
|
|
"computedHash": "b77ea99c2e6e97815b373cc476ad4cc1835d3e736867b764602147be71f6c131"
|
|
},
|
|
"writing-great-skills": {
|
|
"source": "mattpocock/skills",
|
|
"sourceType": "github",
|
|
"skillPath": "skills/productivity/writing-great-skills/SKILL.md",
|
|
"computedHash": "dd555ce552f82784c3d2b8d13a8e26a6677a07ddc00032e142dec33bfd5438c6"
|
|
}
|
|
}
|
|
}
|