Drive msfconsole across the workflow - DB-backed recon (dbnmap, auxiliary scanners), version-exploit search/check/run, multi/handler reverse shells (meterpreter-first, plain shellreversetcp backup…
$ npx skills add Encod3d-Sec/TORCH --skill metasploit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Encod3d-Sec/TORCH metasploit --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Encod3d-Sec/TORCH.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/workflow/metasploit .claude/skills/metasploit && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "metasploit" agent skill from https://github.com/Encod3d-Sec/TORCH/tree/main/skills/workflow/metasploit into .claude/skills/metasploit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "metasploit", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Encod3d-Sec/TORCH/tree/main/skills/workflow/metasploitType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Encod3d-Sec/TORCH --skill metasploit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Encod3d-Sec/TORCH metasploit --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Encod3d-Sec/TORCH.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/workflow/metasploit .agents/skills/metasploit && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "metasploit" agent skill from https://github.com/Encod3d-Sec/TORCH/tree/main/skills/workflow/metasploit into .agents/skills/metasploit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "metasploit", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Encod3d-Sec/TORCH --skill metasploit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Encod3d-Sec/TORCH metasploit --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Encod3d-Sec/TORCH.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/workflow/metasploit .cursor/skills/metasploit && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "metasploit" agent skill from https://github.com/Encod3d-Sec/TORCH/tree/main/skills/workflow/metasploit into .cursor/skills/metasploit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "metasploit", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Encod3d-Sec/TORCH.git --path skills/workflow/metasploit--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Encod3d-Sec/TORCH --skill metasploit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Encod3d-Sec/TORCH metasploit --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Encod3d-Sec/TORCH.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/workflow/metasploit .gemini/skills/metasploit && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "metasploit" agent skill from https://github.com/Encod3d-Sec/TORCH/tree/main/skills/workflow/metasploit into .gemini/skills/metasploit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "metasploit", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Encod3d-Sec/TORCH metasploitInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Encod3d-Sec/TORCH --skill metasploit -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Encod3d-Sec/TORCH.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/workflow/metasploit .github/skills/metasploit && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "metasploit" agent skill from https://github.com/Encod3d-Sec/TORCH/tree/main/skills/workflow/metasploit into .github/skills/metasploit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "metasploit", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Encod3d-Sec/TORCH --skill metasploit -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Encod3d-Sec/TORCH metasploit --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Encod3d-Sec/TORCH.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/workflow/metasploit .opencode/skills/metasploit && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "metasploit" agent skill from https://github.com/Encod3d-Sec/TORCH/tree/main/skills/workflow/metasploit into .opencode/skills/metasploit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "metasploit", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
metasploitDrive msfconsole across the workflow - DB-backed recon (dbnmap, auxiliary scanners), version-exploit search/check/run, multi/handler reverse shells (meterpreter-first, plain shellreversetcp backup…
Metasploit is an agent skill from Encod3d-Sec/TORCH. Drive msfconsole across the workflow - DB-backed recon (dbnmap, auxiliary scanners), version-exploit search/check/run, multi/handler reverse shells (meterpreter-first, plain shellreversetcp backup for Windows/EDR), sessions + localexploitsuggester + post modules, and autoroute/portfwd/socks pivoting. Points to the metasploit cheatsheet for syntax. Use for "metasploit", "msfconsole", "msfvenom", "meterpreter", "multi/handler", or driving an exploit/reverse-shell through msf.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Security, covering Penetration testing. It works with Metasploit and Nmap. The repository describes itself as: Karpathy LLM based claude harness for PenetrationTesting / Bugbounty using obsidian. The licence is MIT.
Read from SKILL.md and the folder at commit d21b6c9. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Metasploit loads about 1k tokens when it runs. Until then it costs about 124 tokens; SKILL.md has 461 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from Encod3d-Sec/TORCH at commit d21b6c9, republished under its MIT licence (© Encod3d-Sec). 461 words, ~1,017 tokens.
.claude/skills/metasploit/SKILL.md (or your agent's skills folder).Drive msfconsole for recon, exploit, reverse shells, and post-ex. Syntax lives in
[[metasploit]]; this skill is the workflow that strings it together.
Before firing any exploit module, query the fingerprinted tech/CVE: read [[metasploit]]
directly for syntax, then Skill(arsenal) for the matching module/payload/technique. Never fire
a module from memory when a targeted lookup would confirm the right one/target index.
msfconsole -q in a named tmux tab, never a blind background job, the operator needs to see
sessions land live. workspace -a <eng> scopes loot to the engagement, db_status confirms the
Postgres backend is up before anything else. Cheatsheet: Setup + Database sections.
db_nmap writes straight to hosts/services; layer auxiliary/scanner/* (smb/http/ssh
version + vuln checks) on top for anything plain nmap scripts miss. This complements the
ctf-box Phase-1 basics, it does not replace them, run both.
search <app> <ver> or search cve:<id>, use, info to read the module's CVE refs and
target list, check before run/exploit whenever the module supports it, a non-destructive
exploitability test beats a blind fire. Cheatsheet: Search and Selection + Options and Running.
multi/handler catches. Payload choice: meterpreter first
(linux/x64/meterpreter/reverse_tcp / windows/x64/meterpreter/reverse_tcp), fall back to plain
shell_reverse_tcp when meterpreter is blocked or unstable, routine on hardened Windows/EDR.
Delivery via msfvenom (ELF/EXE/ASPX/PHP, cheatsheet's MSFVenom section has every format).
Egress-test the LPORT (80/443/53 before 4444). Background the handler correctly:
set ExitOnSession false; run -j so it keeps catching new sessions. On the VM, scripts/vm-handler.sh <eng> <lhost> [payload] automates the LPORT choice: it reads the VM's listeners and picks the first FREE egress-friendly port (80/443/53/8000/8080), so the handler never fails to bind on a taken port nor silently picks a filtered high port; it launches in the engagement's msf tmux window and prints the LPORT to build the payload with.
sessions -i to interact, run post/multi/recon/local_exploit_suggester is the privesc reflex
on every fresh session, then targeted post/* modules, getsystem, and
post/multi/manage/shell_to_meterpreter to upgrade a plain shell. Cheatsheet: Sessions and Jobs
autoroute/portfwd/socks through a session to reach internal-only ports before hand-rolling
SSH -L. Full syntax and proxychains setup: [[pivoting]].
Before trusting any shell or privesc claim: getuid + sysinfo/hostname must match the actual
target. A uid=0 that doesn't match the target is the false-root trap, the session died back to
the attacker box. Same guardrail Skill(delegate) enforces on manual exploit runs.
The fiddly msfvenom-compile -> handler-catch -> escalation-run sequence is a prime
Skill(delegate) hand-off: fully specified, mechanical, cheap-model-shaped. DRIVE msf for every
load-bearing exploit/shell request so the operator watches sessions land; don't abandon msf for
raw scripts once a foothold lands.
Sessions, loot, and creds stay in the msf DB workspace + targets/<eng>/; never paste a real
host/cred/hashdump into wiki/ or session/*.
© Encod3d-Sec, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/workflow/metasploit of Encod3d-Sec/TORCH.
Open the folder on GitHubat commit d21b6c9
Metasploit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Metasploit this skillEncod3d-Sec/TORCH | 329 | — | ~1k | Automated safety check: Pass | MIT | |
| Exploiting Ms17 010 Eternalblue Vulnerabilitymukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~963 | Automated safety check: Pass | Apache-2.0 | |
| Add Community Skillsamugit83/redamon | 3k | — | ~775 | Automated safety check: Pass | MIT | |
| NmapBrownFineSecurity/iothackbot | 859 | 1 repos | ~3.8k | Automated safety check: Notes | MIT | |
| Nmap ReconCommonHuman-Lab/nyxstrike | 157 | — | ~639 | Automated safety check: Pass | Custom licence | |
| Operate Network Reconcyberful/cyberful | 135 | — | ~1.1k | Automated safety check: Pass | AGPL-3.0 |
mukul975/Anthropic-Cybersecurity-Skills
Detects and exploits MS17-010 (EternalBlue), a critical remote code execution flaw in Microsoft's SMBv1 implementation, using Nmap's ms-17-010 NSE script for detection and Metasploit's…
samugit83/redamon
Adding a Community Agent Skill: a Markdown attack-workflow file that users import from the catalog, which then competes in the Intent Router and is injected into the agent's system prompt.
BrownFineSecurity/iothackbot
Professional network reconnaissance and port scanning using nmap.
CommonHuman-Lab/nyxstrike
Network reconnaissance workflow using nmap, masscan, and rustscan via NyxStrike tools
cyberful/cyberful
Build a high-fidelity network and service inventory using Nmap, Masscan, packet capture, DNS, and protocol-specific follow-up.
AgentSecOps/SecOpsAgentKit
Network reconnaissance and security auditing using Nmap for port scanning, service enumeration, and vulnerability detection.
Encod3d-Sec/TORCH
Runs a bug-bounty engagement through a script that tracks the current pass, builds a board of rows from recon and prints the next required action each turn.
Encod3d-Sec/TORCH
Checks that the bb, pt and ctf workflow driver is set up correctly on a machine: vault content, skill symlinks, hooks, imports and a live smoke test, with fixes for failures.
Encod3d-Sec/TORCH
Opens a visible Chromium window on a Kali VM so an operator can complete a manual login or CAPTCHA while the agent watches and acts through the chrome-devtools MCP.
Encod3d-Sec/TORCH
Runs a capture-the-flag box from first scan to root with a driver script that tracks progress and prints the next action each turn.
Encod3d-Sec/TORCH
Decides when a main pentesting agent should hand a fully-specified, mechanical exploit-compile or privilege-escalation step to a cheaper sub-agent, and how to specify that handoff safely.
Encod3d-Sec/TORCH
Adaptive web fuzzing for pentests, bug bounty and CTF work: picks the smallest suitable SecLists wordlist per target surface and calibrates filters against soft-404 responses.
Works with
Categories
Drive msfconsole across the workflow - DB-backed recon (dbnmap, auxiliary scanners), version-exploit search/check/run, multi/handler reverse shells (meterpreter-first, plain shellreversetcp backup…. Metasploit is an agent skill from Encod3d-Sec/TORCH. Drive msfconsole across the workflow - DB-backed recon (dbnmap, auxiliary scanners), version-exploit search/check/run, multi/handler reverse shells (meterpreter-first, plain shellreversetcp backup for Windows/EDR), sessions + localexploitsuggester + post modules, and autoroute/portfwd/socks pivoting.
Metasploit fits situations like: driving an exploit/reverse-shell through msf; tasks that involve Penetration testing.
Run `npx skills add Encod3d-Sec/TORCH --skill metasploit -a claude-code`. Or copy the skill folder (skills/workflow/metasploit in Encod3d-Sec/TORCH) into .claude/skills/metasploit in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Encod3d-Sec/TORCH --skill metasploit -a codex`. Or copy the skill folder (skills/workflow/metasploit in Encod3d-Sec/TORCH) into .agents/skills/metasploit in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Encod3d-Sec/TORCH --skill metasploit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/metasploit, .gemini/skills/metasploit, .github/skills/metasploit and .opencode/skills/metasploit in your project.
SKILL.md names no scripts, command-line tools or credentials: Metasploit is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Metasploit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Metasploit: Exploiting Ms17 010 Eternalblue Vulnerability (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Add Community Skill (samugit83/redamon, 3k stars), Nmap (BrownFineSecurity/iothackbot, 859 stars) and Nmap Recon (CommonHuman-Lab/nyxstrike, 157 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Encod3d-Sec (a GitHub user) maintains it in Encod3d-Sec/TORCH, which has 329 GitHub stars. The repository holds 35 skills in this directory. The repository was last updated on September 1, 2026.
Source: Encod3d-Sec/TORCH on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
