Run a professional penetration engagement OR a network vulnerability scan from a scope. WEB mode (apex domains / app URLs) — mandatory surface expansion, systematic OWASP attack-class coverage, reversible active exploitation, authoritative validation, Transilience PDF. NETWORK mode (a list of IPs/CIDRs, e.g. 1500 hosts) — machine-prudent BATCHED tool-first nmap sweep (host discovery + bounded common+less-common port/service scan + CVE surfacing) with a uniform per-IP output tree, then bounded deep-dives on the highest-value hosts. The general (non-CTF) analogue of hackthebox/htb-solve.
中文简介正在准备中。当前显示原文说明。
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Orchestrates a scoped pentest end-to-end via the pentest-engagement workflow. It is the breadth-complete, coverage-gated counterpart to the flag-shaped htb-solve — same engine (coordinator-loop, now with interleaved per-finding validation built into the loop), but driven by an attack-class coverage matrix instead of a flag, with surface expansion and root-cause severity baked in.
A real (non-CTF) engagement defined by a scope — either:
The workflow auto-detects the mode in Setup (engagement_kind): predominantly IPs/CIDRs → network; apex domains / app URLs → web. For HackTheBox/CTF use hackthebox (htb-solve) instead.
WEB — from a scope file or inline:
Workflow('pentest-engagement', { scope_file: 'projects/pentest/<engagement>-scope.md' })
Workflow('pentest-engagement', { scope: { engagement_name, apex_domains:[], assets:[...], creds_env:[...], roe, business_tier } })
NETWORK — inline IP/CIDR list or a scope file containing one (a plain newline list of IPs/CIDRs is accepted):
Workflow('pentest-engagement', { targets: ['10.0.0.0/24', '192.0.2.0/24', '198.51.100.7'] })
Workflow('pentest-engagement', { scope_file: 'projects/pentest/<engagement>-ips.txt', scan_profile: 'standard' })
Options (shared): maxConcurrent (default = prudent, derived from CPU cores — ~half the cores, capped 2–8; never hundreds/thousands of parallel tasks), dryRun, max_experiments, business_tier, report (default true).
Options (network): scan_profile light (bounded 1-1024 + curated less-common, for large/fast sweeps) / standard (full-range -p- on every reachable host, DEFAULT; two-stage SYN→-sV on found-open ports, host-count-guarded, message-bus + non-443-TLS aware) / full (-p- + bounded UDP); udp (top-50 UDP; off for light/standard, auto-on for full); slice_size (hosts per scan worker, auto ≈64 IP-list / 2 CIDR-heavy); deepen_top (deep-dive the N highest-value hosts, default 10, 0 to skip); geo_vantages (≤2 gcp zones for the 2nd-vantage allowlist re-probe; overrides the US+EU default), auto_provision (default true; false = detect+flag only, no cloud spend). On a source-IP/geo-allowlist signature the workflow auto-provisions a 2nd-geography vantage and re-probes the filtered hosts before concluding "no surface."
Write the scope file per reference/scope-file-format.md. Credentials are referenced by env-var name only and read from the repo .env via python3 tools/env-reader.py — never inline secret values.
env-reader creds, parse scope, classify kind (web|network), read CPU cores → prudent parallel-task cap, OUTPUT_DIR = projects/pentest/<date>_<engagement>/, STARTED Slack (gated).crt.sh, certspotter, subfinder, origin-discovery for CDN/WAF-fronted hosts). Scope = the discovered surface, not the handoff. Builds the per-asset work list + seeds each asset's coverage matrix.
Scan (NETWORK, replaces Expand) — slice the IP/CIDR set into machine-prudent batches; one nmap worker per slice (agents scale with slices ≈ dozens, never with IP count) runs the SAME pipeline: host discovery (reachability is unknown) → bounded common+less-common port/service scan → CVE surfacing (nmap --script vulners, nuclei, each CVE-ID enriched via tools/nvd-lookup.py) → writes a uniform per-IP tree hosts/<ip>/{recon,host.json,findings} + a merged recon/inventory/.coordinator-loop (coverage mode), which validates each candidate the instant it is materialized on fresh blind agents (strict per-finding cure/drop loop) before search continues. NETWORK: bounded coordinator-loop deep-dives on only the deepen_top highest-value hosts, same interleaved per-finding validation (everything else is the uniform tool-scan, not a per-host agent). Coverage-by-VALID: a class is covered only by a VALID/REPAIRED finding, a justified N/A, or a genuine negative — a class whose candidates were all rejected/dropped stays pending and search keeps going.attack-path-stitcher + risk-prioritiser across all validated findings → ranked org roadmap.tools/report_data_build.py merges the namespaced interim finding-JSONs into the canonical report_data.json (the sole-owner assembly), then the format-dispatched renderer runs — transilience → the canonical generate_report.py PDF skill, custom → custom_report_cmd (or a Markdown fallback). JS then hard-gates: report_data assembled ∧ (transilience: WROTE ∧ bytes>0 ∧ the [assets: …/formats/transilience-report-style] provenance tag), retry-once → BLOCKED. Only VALID/REPAIRED findings appear (drop-entirely — validated/ is confirmed-only by construction); REJECTED (false-positives/) and uncured DROPPED (dropped/) never appear and there is no gaps/assurance section. The finalize runner also runs network_coverage_map.py (swept-host tail) + coverage_gate.py over the whole engagement, writes reports/coverage-matrix.json, and the deliverable includes a deterministic Attack Pattern Coverage section (surface-unit × attack-class). COMPLETE is a hard 100% gate: it requires the report to assemble+render AND the coverage gate to report complete:true (every applicable cell covered) — for BOTH web and network (network additionally requires scan-completion). Any untested applicable cell → INCOMPLETE_coverage / BLOCKED.<report_id>_deliverable.zip (reports/ input/ logs/ artifacts/), a short stats summary (summary.md: agents, findings by severity, elapsed; tokens/cost render unavailable — no runtime token counter), and the workflow returns slack_offer: true.Post-run (main loop, outside the workflow): because coordinators must not call AskUserQuestion, the invoking agent shows the returned summary and asks whether to post the deliverable_zip to Slack; on yes, python3 tools/slack-send.py --channel "$PENTEST_SLACK_CHANNEL_ID" (gated on a successful, COMPLETE engagement).
Report options: report_format transilience (default) | custom; custom_report_cmd (the custom renderer, receives the report_data.json path + reports/ dir); prior_report (a prior PDF or report_data.json — its title/sector/scope are metadata-only, never seeding the work list) + version to mint the cover version + "Supersedes" line.
The decision layer is a frozen pure-JS computeVerdict (parity-guarded, fixture-pinned), its operands are frozen per engagement via NVD/KEV --cache-dir snapshots (artifacts/nvd-cache/, artifacts/kev-snapshot.json), and the adversarial quorum is raised to 3. Given identical inputs the verdict is provably identical. But a fresh live run is highly reproducible, not 100% — LLM sampling produces the booleans/numbers that feed the verdict, and live-target drift moves the inputs; that ceiling is inherent and stated plainly, not papered over. Byte-identical results are a guarantee 100% only on replay of a frozen evidence set (the Phase-2 replay cache, artifacts/validation-cache/) — that is the sole context in which "same request → same result" is a guarantee rather than a strong tendency.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Offensive AI security testing and exploitation framework. Systematically tests LLM applications for OWASP Top 10 vulnerabilities including prompt injection, model extraction, data poisoning, and supply chain attacks. Integrates with pentest workflows to discover and exploit AI-specific threats.
中文简介正在准备中。当前显示原文说明。
API security testing - GraphQL, REST API, WebSocket, and Web-LLM attack techniques.
中文简介正在准备中。当前显示原文说明。
Stitches confirmed single-asset findings into multi-hop attack paths across the organization. Builds a graph where nodes are assets and edges are confirmed exploit hops citing the findings that enable them.
中文简介正在准备中。当前显示原文说明。
Acquire an authenticated session THROUGH MFA/OTP on an in-scope target and emit a reusable session artifact (Playwright storageState + Bearer) so executors can test the post-auth attack surface. Use when the highest-value authenticated classes (BOLA/IDOR/mass-assignment/injection on the real data APIs) are blocked because login is gated by SMS-OTP or TOTP MFA. Distinct from the authentication skill (which ATTACKS auth); this one legitimately authenticates and hands the session to the rest of the engagement.
中文简介正在准备中。当前显示原文说明。
Authentication security testing - auth bypass, JWT attacks, OAuth flaws, password attacks, 2FA bypass, CAPTCHA bypass, and bot detection evasion.
中文简介正在准备中。当前显示原文说明。
Smart contract security testing and blockchain CTF exploitation. Covers Solidity vulnerability analysis, EVM storage manipulation, delegatecall attacks, CREATE/CREATE2 address prediction, and common DeFi exploit patterns. Use when analyzing Solidity contracts, solving blockchain challenges, or testing smart contract security.
中文简介正在准备中。当前显示原文说明。