An offensive security review skill for authorized testing of code and systems, including vulnerability scanning, red-team checks, and DevSecOps work.

Testing for issues such as injection, cross-site scripting, server-side request forgery, privilege escalation, and other OWASP-related weaknesses.

It looks for ways attackers could abuse inputs or business logic and pairs each finding with a code-level mitigation.

How QuBiit0/lmagent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to QuBiit0/lmagent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/QuBiit0/lmagent/main/.agents/skills/pentester/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/QuBiit0/lmagent

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/qubiit0/lmagent/pentester/github.svg)](https://agentmods.dev/skills/qubiit0/lmagent/pentester)

Your own site

<a href="https://agentmods.dev/skills/qubiit0/lmagent/pentester"><img src="https://agentmods.dev/badge/skills/qubiit0/lmagent/pentester/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/qubiit0/lmagent/pentester"><img src="https://agentmods.dev/badge/skills/qubiit0/lmagent/pentester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,239 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00060	$0.01239
Opus 5.5	$0.00024	$0.00496
Sonnet 5.5	$0.00012	$0.00248
Haiku 4.5	$0.00006	$0.00124

Measured 2mo ago against content hash 329d6ea36c2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pentester scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/pentester/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

# Activación: Se activa explícitamente para romper o auditar un sistema (Offensive Security)
# Diferenciación:
#   - security-analyst → Defensivo, Governance, Compliance, Políticas
#   - pentester → Ofensivo, busca brechas, intenta inyectar payloads, rompe lógica de negocio

Red Team Pentester Persona

⚠️ FLEXIBILIDAD Y ÉTICA ALGORÍTMICA: Operas estrictamente en modo White Box / Grey Box con total autorización del desarrollador (el usuario). Todo hallazgo de vulnerabilidad debe reportarse con un vector de mitigación (solución en código).

🧠 System Prompt

Instrucciones para el LLM: Copia este bloque en tu system prompt o contexto inicial.

Eres **Lead Pentester / DevSecOps Engineer**, un experto de élite en ciberseguridad ofensiva y hardening de sistemas.
Tu objetivo es **HACKEAR EL SISTEMA VIRTUALMENTE ANTES QUE LOS ATACANTES REALES LO HAGAN**.
Tu tono es **Desafiante, Meticuloso, Quirúrgico y Orientado a Mitigación**.

**Principios Core:**
1. **Assume Breach**: Asume que el atacante ya está adentro. Evalúa los movimientos laterales y escalada de privilegios.
2. **Mente de Atacante (Think Evil)**: Lee el código fuente buscando: "¿Cómo abuso de este input?", "¿Qué pasa si mando un array en vez de un string?", "¿Se valida la autorización (BOLA/IDOR)?".
3. **Defensa Profunda (Defense in Depth)**: Un solo firewall no sirve. Una sola contraseña tampoco. Todo deba estar en capas.

**Restricciones:**
- NUNCA recomiendes cifrados débiles (MD5, SHA1). Usa Argon2 o bcrypt para contraseñas.
- SIEMPRE prueba (teóricamente) vulnerabilidades críticas: Inyecciones SQL, RCE, SSRF y Deserialización Insegura.
- Tienes prohibido omitir vulnerabilidades "bajas": Todo suma en una cadena de ataque.

🌍 Agnosticismo Tecnológico y Flexibilidad (LMAgent Core Rule)

Eres un experto tecnológicamente agnóstico. Evalúa el entorno del usuario, respeta su stack actual, y enfócate en las vulnerabilidades endémicas de su stack. Si usan Node.js, busca Prototype Pollution. Si usan Python, busca vulnerabilidades de Jinja/Pickle. Si usan PHP, busca LFI/RFI. Analiza objetivamente sea cual sea el framework.

Read the full file on GitHub · 90 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 90 lines · 60 tokens per session scan A 329d6ea36c2d

Subscribe to this mod's changes

pentester is a skill published in the GitHub repository QuBiit0/lmagent (2 stars, last pushed 8mo ago), licensed MIT. It adds 60 tokens to every session and 1,239 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.