[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DEGSM8DSPW76P5B0PH6SWH":3,"skill-same:01M7DEGSM8DSPW76P5B0PH6SWH":70},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":14,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":45,"install":46,"resources":59},"01M7DEGSM8DSPW76P5B0PH6SWH","raptix",null,"Drive Raptix — an autonomous multi-agent red-team framework — over MCP to run authorized penetration tests and bug-bounty engagements end to end, then watch and steer them live from chat. Launch an engagement against a target, poll its transcript to narrate progress, send messages to refocus it, and pull findings as SARIF. Use when the user asks to run a pentest\u002Fred-team engagement, hunt a bug bounty, do recon, exploit\u002Fscan a host, web app, API, network, cloud, Active Directory, mobile app, or smart contract WITH Raptix — or to check\u002Fresume a running engagement or report what Raptix found. Triggers: run a raptix engagement, pentest this with raptix, bug bounty, recon this target, red team this, scan this host, resume the engagement, what did raptix find, raptix status. Do NOT use for ad-hoc local tool runs (running nmap\u002Fsqlmap\u002Fffuf directly) when no Raptix server is involved — this drives the Raptix orchestrator, not raw tools.","Akapi895\u002Fraptix","Akapi895","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F83953516?v=4","01M7DEGNDGERR4F4YETDFVA512","Phạm Anh Tuấn","01M7DEGNEHYZNA920AYM5EH7H8",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FAkapi895\u002Fraptix\u002Fblob\u002Fmaster\u002Fintegrations\u002Fagent-skills\u002Fraptix\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: raptix\ndescription: \"Drive Raptix — an autonomous multi-agent red-team framework — over MCP to run authorized penetration tests and bug-bounty engagements end to end, then watch and steer them live from chat. Launch an engagement against a target, poll its transcript to narrate progress, send messages to refocus it, and pull findings as SARIF. Use when the user asks to run a pentest\u002Fred-team engagement, hunt a bug bounty, do recon, exploit\u002Fscan a host, web app, API, network, cloud, Active Directory, mobile app, or smart contract WITH Raptix — or to check\u002Fresume a running engagement or report what Raptix found. Triggers: run a raptix engagement, pentest this with raptix, bug bounty, recon this target, red team this, scan this host, resume the engagement, what did raptix find, raptix status. Do NOT use for ad-hoc local tool runs (running nmap\u002Fsqlmap\u002Fffuf directly) when no Raptix server is involved — this drives the Raptix orchestrator, not raw tools.\"\nversion: 2.0.0\nlicense: Apache-2.0\nmetadata:\n  homepage: \"https:\u002F\u002Fgithub.com\u002FAkapi895\u002Fraptix\"\n  hermes:\n    tags: [raptix, red-teaming, penetration-testing, bug-bounty, mcp, autonomous-agents, recon, exploitation, sarif]\n    related_skills: [pentest-recon, offensive-reporting, reconnaissance]\n---\n\n# Raptix engagements (over MCP)\n\nDrive **Raptix** — an autonomous multi-agent red-team framework — as if its\nCLI were in this chat. Run an authorized engagement end to end (recon →\nexploitation → post-exploitation → reporting) across web, API, network, Active\nDirectory, cloud, mobile, smart-contract, and binary targets, then **watch it\nprogress and steer it as it runs**.\n\nYou interact through the `raptix_*` MCP tools (listed below). The heavy\nwork runs inside the Raptix server; you are the operator at the console.\n\n## Mental model — read this first\n\n- An **engagement is a thread.** `raptix_start_engagement` returns a\n  `thread_id`. That is the handle for *every* other tool — there are no run\n  ids to track.\n- The **orchestrator** (`raptix` graph) builds an OPPLAN and delegates to\n  specialist sub-agents (recon, exploit, postexploit, analyst, reverser,\n  cloud_hunter, ad_operator, mobile_operator, …) via a `task()` tool. You watch\n  that narrative and nudge it.\n- Engagements are **long and asynchronous** (minutes to hours). `start` returns\n  immediately; you **poll** and narrate. **Never block** waiting for completion.\n\n## Authorization — non-negotiable\n\n- Only start engagements against assets the user has **explicitly confirmed are\n  in scope**. If scope is unclear or missing, **ask before starting** — do not\n  guess a target.\n- ALWAYS pass scope + rules of engagement in `instruction`: name the in-scope\n  hosts\u002Fdomains\u002Fpaths **and the explicit out-of-scope** items. The orchestrator\n  enforces RoE on every tool call, but you are responsible for giving it\n  correct scope.\n- Decline targets that are plainly not the user's to test.\n\n## Prerequisites (verify on first failure)\n\n- A Raptix **LangGraph server** must be running and reachable\n  (`RAPTIX_API_URL`, default `http:\u002F\u002Flocalhost:2024`). If a tool errors with\n  a connection failure, tell the user to start it (`langgraph dev` or the Docker\n  stack) — don't retry blindly.\n- The `raptix` MCP server must be registered and launched with\n  `RAPTIX_SKIP_BOOT=1` (fast start). See the integration docs.\n\n## Tools\n\n| Tool | Use it to | Key args | Returns (key fields) |\n|------|-----------|----------|----------------------|\n| `raptix_list_graphs` | see available graphs | — | `[{graph_id, name}]` |\n| `raptix_list_engagements` | browse \u002F resume | `limit` | `[{thread_id, engagement_name, status}]` |\n| `raptix_start_engagement` | launch | `targets[]`, `instruction`, `scan_mode`, `engagement_name?` | `{thread_id, engagement_name, run_id, status}` |\n| `raptix_transcript` | watch the narrative | `thread_id`, `after_index`, `limit` | `{messages[], next_index, total, run_status}` |\n| `raptix_watch` | live sub-agent burst | `thread_id`, `max_seconds`, `max_events` | `{events[], run_status}` |\n| `raptix_send_message` | steer \u002F answer \u002F `\u002Fmodel` | `thread_id`, `message` | `{run_id, status}` |\n| `raptix_engagement_state` | OPPLAN \u002F scope \u002F phase | `thread_id` | `{engagement_name, message_count, values}` |\n| `raptix_engagement_status` | run status + findings ready | `thread_id`, `engagement_name?` | `{status, findings_available}` |\n| `raptix_engagement_findings` | pull results | `engagement_name`, `include_sarif?` | `{available, result_count, level_counts, sarif?}` |\n| `raptix_cancel_engagement` | stop the run | `thread_id` | text |\n\nFull parameters, defaults, clamps, and return schemas are in\n[`reference.md`](reference.md). Worked end-to-end runs are in\n[`examples.md`](examples.md).\n\n## The core loop\n\n1. **Pick a graph.** Usually `raptix` (full kill chain). Use `recon` for\n   recon-only, `soundwave` for planning. `raptix_list_graphs()` if unsure.\n2. **Start.** `raptix_start_engagement(targets=[…], instruction=\"In scope: …;\n   Out of scope: …\", scan_mode=\"standard\")`. Save `thread_id` **and**\n   `engagement_name`.\n3. **Watch + narrate.** Loop `raptix_transcript(thread_id,\n   after_index=\u003Cprevious next_index>)`; summarise only the NEW messages for the\n   user (coordinator decisions, `task(\u003Cspecialist>)` delegations, results). For\n   a live burst use `raptix_watch(thread_id)`. Check\n   `raptix_engagement_status(thread_id, engagement_name)`; stop polling when\n   `status` is terminal **or** `findings_available` is true.\n4. **Steer** when useful: `raptix_send_message(thread_id, \"skip the staging\n   host, focus on the API\")`, answer the coordinator, or switch models with\n   `\u002Fmodel anthropic\u002Fclaude-opus-4-8`.\n5. **Report.** When findings exist:\n   `raptix_engagement_findings(engagement_name, include_sarif=true)` →\n   present severity, counts, and reproduction. `raptix_engagement_state` for\n   the OPPLAN\u002Fphase.\n6. **Resume later.** `raptix_list_engagements()` → reuse any `thread_id`.\n\n## Polling cadence (phone \u002F chat friendly)\n\n- Don't spam tools. While running, poll the transcript every ~15–30s and give\n  the user a **1–2 line update per poll**, not raw dumps.\n- Use the returned `next_index` as your cursor so each update covers only new\n  activity.\n- `raptix_watch` blocks up to `max_seconds` (≤45) — use it for a quick live\n  glimpse, not as your main loop.\n\n## Interpreting results (fast guide)\n\n- **transcript.messages**: `role` is user\u002Fassistant\u002Ftool. `tool_calls` like\n  `task(recon)` means a specialist was dispatched. `tool` messages carry results.\n- **status**: `pending`\u002F`running` = working; `success` = finished;\n  `error`\u002F`timeout`\u002F`interrupted` = stopped (say why; offer resume\u002Frestart);\n  `none` = no run yet.\n- **findings**: `available=false` → not persisted yet, keep polling.\n  `level_counts` maps SARIF level → count (`error` = critical\u002Fhigh, `warning` =\n  medium, `note` = low). Pass `include_sarif=true` to mine reproduction details.\n- **engagement_state.values**: OPPLAN, objectives, scope, phase, working files.\n\n## Errors & recovery\n\n- **Connection failure** → the Raptix server isn't up at `RAPTIX_API_URL`.\n  Ask the user to start it; don't loop.\n- **`findings_available=false` for a while** → normal early on; keep watching the\n  transcript and report progress.\n- **`status=error`\u002F`timeout`** → read the last transcript messages for the cause,\n  summarise it, and offer to `send_message` a fix or start fresh.\n- **No active run on `watch`\u002F`cancel`** → the engagement is idle\u002Ffinished; use\n  `transcript`\u002F`findings` instead.\n\nSee [`reference.md`](reference.md) and [`examples.md`](examples.md) for depth.\n","# Raptix engagements (over MCP)\n\nDrive **Raptix** — an autonomous multi-agent red-team framework — as if its\nCLI were in this chat. Run an authorized engagement end to end (recon →\nexploitation → post-exploitation → reporting) across web, API, network, Active\nDirectory, cloud, mobile, smart-contract, and binary targets, then **watch it\nprogress and steer it as it runs**.\n\nYou interact through the `raptix_*` MCP tools (listed below). The heavy\nwork runs inside the Raptix server; you are the operator at the console.\n\n## Mental model — read this first\n\n- An **engagement is a thread.** `raptix_start_engagement` returns a\n  `thread_id`. That is the handle for *every* other tool — there are no run\n  ids to track.\n- The **orchestrator** (`raptix` graph) builds an OPPLAN and delegates to\n  specialist sub-agents (recon, exploit, postexploit, analyst, reverser,\n  cloud_hunter, ad_operator, mobile_operator, …) via a `task()` tool. You watch\n  that narrative and nudge it.\n- Engagements are **long and asynchronous** (minutes to hours). `start` returns\n  immediately; you **poll** and narrate. **Never block** waiting for completion.\n\n## Authorization — non-negotiable\n\n- Only start engagements against assets the user has **explicitly confirmed are\n  in scope**. If scope is unclear or missing, **ask before starting** — do not\n  guess a target.\n- ALWAYS pass scope + rules of engagement in `instruction`: name the in-scope\n  hosts\u002Fdomains\u002Fpaths **and the explicit out-of-scope** items. The orchestrator\n  enforces RoE on every tool call, but you are responsible for giving it\n  correct scope.\n- Decline targets that are plainly not the user's to test.\n\n## Prerequisites (verify on first failure)\n\n- A Raptix **LangGraph server** must be running and reachable\n  (`RAPTIX_API_URL`, default `http:\u002F\u002Flocalhost:2024`). If a tool errors with\n  a connection failure, tell the user to start it (`langgraph dev` or the Docker\n  stack) — don't retry blindly.\n- The `raptix` MCP server must be registered and launched with\n  `RAPTIX_SKIP_BOOT=1` (fast start). See the integration docs.\n\n## Tools\n\n| Tool | Use it to | Key args | Returns (key fields) |\n|------|-----------|----------|----------------------|\n| `raptix_list_graphs` | see available graphs | — | `[{graph_id, name}]` |\n| `raptix_list_engagements` | browse \u002F resume | `limit` | `[{thread_id, engagement_name, status}]` |\n| `raptix_start_engagement` | launch | `targets[]`, `instruction`, `scan_mode`, `engagement_name?` | `{thread_id, engagement_name, run_id, status}` |\n| `raptix_transcript` | watch the narrative | `thread_id`, `after_index`, `limit` | `{messages[], next_index, total, run_status}` |\n| `raptix_watch` | live sub-agent burst | `thread_id`, `max_seconds`, `max_events` | `{events[], run_status}` |\n| `raptix_send_message` | steer \u002F answer \u002F `\u002Fmodel` | `thread_id`, `message` | `{run_id, status}` |\n| `raptix_engagement_state` | OPPLAN \u002F scope \u002F phase | `thread_id` | `{engagement_name, message_count, values}` |\n| `raptix_engagement_status` | run status + findings ready | `thread_id`, `engagement_name?` | `{status, findings_available}` |\n| `raptix_engagement_findings` | pull results | `engagement_name`, `include_sarif?` | `{available, result_count, level_counts, sarif?}` |\n| `raptix_cancel_engagement` | stop the run | `thread_id` | text |\n\nFull parameters, defaults, clamps, and return schemas are in\n[`reference.md`](reference.md). Worked end-to-end runs are in\n[`examples.md`](examples.md).\n\n## The core loop\n\n1. **Pick a graph.** Usually `raptix` (full kill chain). Use `recon` for\n   recon-only, `soundwave` for planning. `raptix_list_graphs()` if unsure.\n2. **Start.** `raptix_start_engagement(targets=[…], instruction=\"In scope: …;\n   Out of scope: …\", scan_mode=\"standard\")`. Save `thread_id` **and**\n   `engagement_name`.\n3. **Watch + narrate.** Loop `raptix_transcript(thread_id,\n   after_index=\u003Cprevious next_index>)`; summarise only the NEW messages for the\n   user (coordinator decisions, `task(\u003Cspecialist>)` delegations, results). For\n   a live burst use `raptix_watch(thread_id)`. Check\n   `raptix_engagement_status(thread_id, engagement_name)`; stop polling when\n   `status` is terminal **or** `findings_available` is true.\n4. **Steer** when useful: `raptix_send_message(thread_id, \"skip the staging\n   host, focus on the API\")`, answer the coordinator, or switch models with\n   `\u002Fmodel anthropic\u002Fclaude-opus-4-8`.\n5. **Report.** When findings exist:\n   `raptix_engagement_findings(engagement_name, include_sarif=true)` →\n   present severity, counts, and reproduction. `raptix_engagement_state` for\n   the OPPLAN\u002Fphase.\n6. **Resume later.** `raptix_list_engagements()` → reuse any `thread_id`.\n\n## Polling cadence (phone \u002F chat friendly)\n\n- Don't spam tools. While running, poll the transcript every ~15–30s and give\n  the user a **1–2 line update per poll**, not raw dumps.\n- Use the returned `next_index` as your cursor so each update covers only new\n  activity.\n- `raptix_watch` blocks up to `max_seconds` (≤45) — use it for a quick live\n  glimpse, not as your main loop.\n\n## Interpreting results (fast guide)\n\n- **transcript.messages**: `role` is user\u002Fassistant\u002Ftool. `tool_calls` like\n  `task(recon)` means a specialist was dispatched. `tool` messages carry results.\n- **status**: `pending`\u002F`running` = working; `success` = finished;\n  `error`\u002F`timeout`\u002F`interrupted` = stopped (say why; offer resume\u002Frestart);\n  `none` = no run yet.\n- **findings**: `available=false` → not persisted yet, keep polling.\n  `level_counts` maps SARIF level → count (`error` = critical\u002Fhigh, `warning` =\n  medium, `note` = low). Pass `include_sarif=true` to mine reproduction details.\n- **engagement_state.values**: OPPLAN, objectives, scope, phase, working files.\n\n## Errors & recovery\n\n- **Connection failure** → the Raptix server isn't up at `RAPTIX_API_URL`.\n  Ask the user to start it; don't loop.\n- **`findings_available=false` for a while** → normal early on; keep watching the\n  transcript and report progress.\n- **`status=error`\u002F`timeout`** → read the last transcript messages for the cause,\n  summarise it, and offer to `send_message` a fix or start fresh.\n- **No active run on `watch`\u002F`cancel`** → the engagement is idle\u002Ffinished; use\n  `transcript`\u002F`findings` instead.\n\nSee [`reference.md`](reference.md) and [`examples.md`](examples.md) for depth.\n",{"name":5,"license":15,"version":24,"metadata":25,"description":7},"2.0.0",{"hermes":26,"homepage":40},{"tags":27,"related_skills":36},[5,28,29,30,31,32,33,34,35],"red-teaming","penetration-testing","bug-bounty","mcp","autonomous-agents","recon","exploitation","sarif",[37,38,39],"pentest-recon","offensive-reporting","reconnaissance","https:\u002F\u002Fgithub.com\u002FAkapi895\u002Fraptix","master","8e5d356b795eae2edd4a26509a4b8968e2c4c251","integrations\u002Fagent-skills\u002Fraptix","https:\u002F\u002Fgithub.com\u002FAkapi895","2026-11-06 17:46:09",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add Akapi895\u002Fraptix --skill raptix",{"tool":52,"command":53},"bunx","bunx skills add Akapi895\u002Fraptix --skill raptix",{"tool":55,"command":56},"pnpm","pnpm dlx skills add Akapi895\u002Fraptix --skill raptix","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAkapi895\u002Fraptix\u002Fblob\u002Fmaster\u002Fintegrations\u002Fagent-skills\u002Fraptix\u002FSKILL.md",true,[60,66],{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"examples.md","REFERENCE","参考文档",4692,"https:\u002F\u002Fgithub.com\u002FAkapi895\u002Fraptix\u002Fblob\u002Fmaster\u002Fintegrations\u002Fagent-skills\u002Fraptix\u002Fexamples.md",{"path":67,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":68,"sourceHtmlUrl":69},"reference.md",6165,"https:\u002F\u002Fgithub.com\u002FAkapi895\u002Fraptix\u002Fblob\u002Fmaster\u002Fintegrations\u002Fagent-skills\u002Fraptix\u002Freference.md",[71,78,85,92,99,106],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7DGM32SRP4FZSPYWY621BKQ","wps-pixie-dust","WPS Pixie-Dust offline nonce attack (reaver -K \u002F pixiewps) and fallback online PIN brute (bully) to recover the AP's WPA PSK without capturing a handshake.","https:\u002F\u002Fgithub.com\u002FAkapi895\u002Fraptix\u002Fblob\u002Fmaster\u002Fpackages\u002Fraptix-skills\u002Fraptix_skills\u002Fdefs\u002Fstandard\u002Fwireless\u002Fwps-pixie-dust\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7DGKXXVDTY0KBZZR83VFPZX","wpa3-sae","WPA3-SAE transition-mode downgrade (DragonShift), SSID Confusion CVE-2023-52424, Dragonblood side-channels, and SAE captive-portal credential recovery against WPA3-Personal networks.","https:\u002F\u002Fgithub.com\u002FAkapi895\u002Fraptix\u002Fblob\u002Fmaster\u002Fpackages\u002Fraptix-skills\u002Fraptix_skills\u002Fdefs\u002Fstandard\u002Fwireless\u002Fwpa3-sae\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7DGKSV77ENX3D6TG2HQX9MK","wpa2-psk","WPA\u002FWPA2-PSK handshake capture via targeted deauth + PMKID (no deauth required) + offline hashcat cracking. The most common consumer\u002FSMB encryption mode in 2026.","https:\u002F\u002Fgithub.com\u002FAkapi895\u002Fraptix\u002Fblob\u002Fmaster\u002Fpackages\u002Fraptix-skills\u002Fraptix_skills\u002Fdefs\u002Fstandard\u002Fwireless\u002Fwpa2-psk\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M7DGKJ9R6YTFRFBSEAJRGGKF","wpa-enterprise-eap","WPA\u002FWPA2\u002FWPA3-Enterprise (802.1X\u002FEAP) rogue-RADIUS evil-twin for MSCHAPv2 capture, GTC downgrade, and PEAP relay. MSCHAPv2 capture equals a NetNTLM hash — the primary wireless on-ramp to Active Directory.","https:\u002F\u002Fgithub.com\u002FAkapi895\u002Fraptix\u002Fblob\u002Fmaster\u002Fpackages\u002Fraptix-skills\u002Fraptix_skills\u002Fdefs\u002Fstandard\u002Fwireless\u002Fwpa-enterprise-eap\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M7DGKCFZGKK2EQMWZM1A18S8","krack-fragattacks","KRACK key-reinstallation (CVE-2017-13077..13082) and FragAttacks fragmentation\u002Faggregation flaws (CVE-2020-24586..24588, CVE-2020-26139..26147) against legacy or embedded 802.11 supplicants with poor patch cadence.","https:\u002F\u002Fgithub.com\u002FAkapi895\u002Fraptix\u002Fblob\u002Fmaster\u002Fpackages\u002Fraptix-skills\u002Fraptix_skills\u002Fdefs\u002Fstandard\u002Fwireless\u002Fkrack-fragattacks\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M7DGK76MKZQWBXTZN82W7214","evil-twin-karma","Evil-twin rogue AP with KARMA\u002FMana PNL-probe response, captive-portal credential capture, and post-association MITM for PSK\u002Fopen networks. Distinct from wpa-enterprise-eap which targets 802.1X.","https:\u002F\u002Fgithub.com\u002FAkapi895\u002Fraptix\u002Fblob\u002Fmaster\u002Fpackages\u002Fraptix-skills\u002Fraptix_skills\u002Fdefs\u002Fstandard\u002Fwireless\u002Fevil-twin-karma\u002FSKILL.md",[],[]]