recon-authorized-target
Inventory one user-authorized host, lab target, or CVE reproduction surface.
Skill by MilkSU-Official
Chalk Labs
Need help deploying recon-authorized-target?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/milksu-official-recon-authorized-target
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/recon-authorized-target
What's inside
- Skill name
recon-authorized-target- Description
- Inventory one user-authorized host, lab target, or CVE reproduction surface. Use for wide recon, port or HTTP mapping, and pentest planning on that bound. Do not use to scan unauthorized hosts or invent a typed sweep tool.
- License
- AGPL-3.0
- Instructions
- 19 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Recon an authorized target Map the user-selected target and keep the inventory in the job report. Stay inside the visible authorization for this conversation. ## Establish the bound 1. Read the dossier, lease, or user message that names the exact host, URL, or lab environment. 2. If the target is missing or several candidates remain, call `milksu_ask` before any scan. 3. Do not invent a sweep tool, do not scan internet ranges, and do not move to a host the user has not authorized. ## Plan the inventory Write a short plan in the conversation: which surfaces, which commands, and what evidence belongs in `report.md`. Prefer existing Pi tools (`bash`, `bg_task`, `bg_status`, `read`, isolated browser) and at most four read-only or worker subagent lanes. Watch `bg_status`; do not pile identical background probes. ## Record Put live findings in `report.md` as they appear. Distinguish observed facts, guesses, and items still unchecked. When the inventory is enough to choose a next exploit or reproduction step, stop scanning and ask or continue that step.
From MilkSU-Official/milksu, AGPL-3.0.
More from MilkSU-Official/milksu
- 0.651score
create-technical-deliverables
MilkSU-Official
Write a readable, reproducible report, runbook, write-up, or script note.
SkillAFreshness: A★ 31Claude Code +9 - 0.651score
ghidra-rpc
MilkSU-Official
Use when reversing a binary with Ghidra.
SkillAFreshness: A★ 31Claude Code +9 - 0.651score
deep-research-web
MilkSU-Official
Single-turn web research on an open question, ending in a source-grounded report written to the workspace.
SkillAFreshness: A★ 31Claude Code +9 - 0.651score
release-milksu
MilkSU-Official
Build, verify, or publish a MilkSU desktop release.
SkillAFreshness: A★ 31Claude Code +9 - 0.651score
reverse-engineer-anything
MilkSU-Official
Reverse engineer shipped artifacts (native binaries, Electron/ASAR, .NET assemblies, APKs, archives) with the milksu-rea MCP tools when a claim depends on a…
SkillAFreshness: A★ 31Claude Code +9 - 0.648score
review-security
MilkSU-Official
Review credentials, authorization, input boundaries, filesystem or network scope, and external side effects.
SkillAFreshness: A★ 31Claude Code +9 - 0.648score
integrate-api
MilkSU-Official
Connect an external API, SDK, OAuth, webhook, or hosted model using current official docs and a verified request.
SkillAFreshness: A★ 31Claude Code +9 - 0.648score
deep-research
MilkSU-Official
Use for scoped deep-research questions that need multiple sources and a source-backed synthesis.
SkillAFreshness: A★ 31Claude Code +9 - 0.648score
frontend-visual-qa
MilkSU-Official
Review or fix web UI with a live preview and MilkSU's isolated Coding Browser.
SkillAFreshness: A★ 31Claude Code +9 - 0.648score
product-design
MilkSU-Official
Set the visual goal for a major UI or flow change, then implement and verify the rendered result.
SkillAFreshness: A★ 31Claude Code +9 - 0.646score
jadx
MilkSU-Official
Use when decompiling an Android APK, DEX, or AAR to Java.
SkillAFreshness: A★ 31Claude Code +9
Signals
- Stars
- 31
- Forks
- 6
- Open issues
- 8
- Last commit (this folder)
- Sep 26, 2026 (1 month ago)
- Last release
- Sep 27, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- AGPL-3.0
- Repository
- github.com/MilkSU-Official/milksu
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from MilkSU-Official
- 0.651score
create-technical-deliverables
MilkSU-Official
Write a readable, reproducible report, runbook, write-up, or script note.
SkillAFreshness: A★ 31Claude Code +9 - 0.651score
ghidra-rpc
MilkSU-Official
Use when reversing a binary with Ghidra.
SkillAFreshness: A★ 31Claude Code +9 - 0.651score
deep-research-web
MilkSU-Official
Single-turn web research on an open question, ending in a source-grounded report written to the workspace.
SkillAFreshness: A★ 31Claude Code +9 - 0.651score
release-milksu
MilkSU-Official
Build, verify, or publish a MilkSU desktop release.
SkillAFreshness: A★ 31Claude Code +9 - 0.651score
reverse-engineer-anything
MilkSU-Official
Reverse engineer shipped artifacts (native binaries, Electron/ASAR, .NET assemblies, APKs, archives) with the milksu-rea MCP tools when a claim depends on a…
SkillAFreshness: A★ 31Claude Code +9 - 0.648score
review-security
MilkSU-Official
Review credentials, authorization, input boundaries, filesystem or network scope, and external side effects.
SkillAFreshness: A★ 31Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get recon-authorized-target running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
recon-authorized-target skill. Agent Mart. https://agentmart.dev/skills/milksu-official-recon-authorized-target (last updated 2026-10-24)