Skip to content
Agentmart
Submit a tool

authorized-pentest-validation

Hard manual gate (disable-model-invocation: true).

Skill by SensLiao

IndexedLicense unknown
Write a review

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/sensliao-authorized-pentest-validation

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.

We use your email only for this newsletter. Privacy

About

Hard manual gate (disable-model-invocation: true). Authorized penetration-testing validation for systems the user owns or is explicitly authorized to test — use ONLY on explicit user request AND with a complete ROE in place. Active validation stays inside the ROE scope: baseline DAST on authorized targets, non-destructive verification of known vulnerabilities, header/cookie/TLS posture, access-control checks with test accounts. NEVER destructive testing, DoS, persistence, credential theft, exfiltration, stealth or out-of-scope scanning. NEVER rename this skill — the phrase `/authorized-pentest-validation` is part of the control surface.

Use cases: testing, security

Reviews

Write a review

No 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. 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/authorized-pentest-validation

Tools it pre-approves 3

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • Read,
  • Write,
  • Bash

What's inside

Skill name
authorized-pentest-validation
Description
Hard manual gate (disable-model-invocation: true). Authorized penetration-testing validation for systems the user owns or is explicitly authorized to test — use ONLY on explicit user request AND with a complete ROE in place. Active validation stays inside the ROE scope: baseline DAST on authorized targets, non-destructive verification of known vulnerabilities, header/cookie/TLS posture, access-control checks with test accounts. NEVER destructive testing, DoS, persistence, credential theft, exfiltration, stealth or out-of-scope scanning. NEVER rename this skill — the phrase `/authorized-pentest-validation` is part of the control surface.
License
unknown
Allowed tools
Read,, Write,, Bash
Instructions
484 lines in SKILL.md · view on GitHub

Before installing

  • Pre-approves any shell command
  • Instructions call the network

Files (1)

  • SKILL.md

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

More from SensLiao/Claude-code-setting

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 3, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
License unknown
Repository
github.com/SensLiao/Claude-code-setting
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from SensLiao

Cite this page

authorized-pentest-validation skill. Agent Mart. https://agentmart.dev/skills/sensliao-authorized-pentest-validation (last updated 2026-10-24)