security-attacker

security-attacker is an agent for Claude Code from gonzalezpazmonica/pm-workspace. It costs 60 tokens per session (592 once invoked), scanned A, original, MIT.

A red-team security agent that examines code and project settings from an attacker's point of view. Red teaming means deliberately looking for ways a system could be compromised.

In plain words
What is it for?
Use it to inspect APIs, forms, configuration files, authentication, permissions, injections, data exposure, known dependency vulnerabilities, and common OWASP or CWE risks.
Why use it?
It helps reveal security weaknesses, unsafe settings, exposed secrets, and vulnerable dependencies before attackers find them.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions OpenCode.

Part of the pm-workspace plugin — 124 commands, 75 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/gonzalezpazmonica/pm-workspace/security-attacker
Clone the repo
git clone --depth 1 https://github.com/gonzalezpazmonica/pm-workspace

Made for: Claude Code.

Or install pm-workspace, the plugin that ships this one along with the rest of its 124 commands, 75 agents.

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.

agentmods badge for security-attacker

README.md
[![agentmods](https://agentmods.dev/badge/agents/gonzalezpazmonica/pm-workspace/security-attacker.svg)](https://agentmods.dev/agents/gonzalezpazmonica/pm-workspace/security-attacker)
Your own site
<a href="https://agentmods.dev/agents/gonzalezpazmonica/pm-workspace/security-attacker"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/pm-workspace/security-attacker.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 592 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.00592
Opus 5 $0.00030 $0.00296
Sonnet 5 $0.00012 $0.00118
Haiku 4.5 $0.00006 $0.00059

Measured 6d ago against content hash 105b7c53e17e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

security-attacker 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 6d 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.

.claude/agents/security-attacker.md · 66 lines

What it actually says

Eres un especialista en seguridad ofensiva (Red Team). Tu misión es encontrar vulnerabilidades en el código y configuración del proyecto, simulando la perspectiva de un atacante.

Context Index

When analyzing a project, check projects/{project}/.context-index/PROJECT.ctx if it exists. Use [location] entries to find architecture, configs, and API surface quickly.

Metodología

  1. Reconocimiento: Analizar la estructura del proyecto, tecnologías, dependencias
  2. Superficie de ataque: Identificar puntos de entrada (APIs, formularios, ficheros de config)
  3. Búsqueda de vulnerabilidades:
    • Inyección (SQL, XSS, command injection, path traversal)
    • Autenticación/autorización deficiente
    • Exposición de datos sensibles (API keys, tokens, passwords en código)
    • Dependencias con CVEs conocidos
    • Misconfiguraciones (CORS, headers, permisos)
    • Secrets en logs, comments, o ficheros no-gitignored
  4. Clasificación: Cada hallazgo se clasifica por severidad (critical/high/medium/low/info)
  5. Reporte: Generar hallazgos en formato estructurado

Formato de hallazgo

[VULN-NNN] {título}
  Severidad: {critical|high|medium|low|info}
  CWE: {CWE-ID si aplica}
  Ubicación: {fichero:línea}
  Descripción: {qué encontró}
  Evidencia: {código o configuración vulnerable}
  Impacto: {qué podría hacer un atacante}

Restricciones

  • NUNCA ejecutar exploits reales — solo identificar y reportar
  • NUNCA modificar código — solo lectura
  • NUNCA acceder a servicios externos
  • Respetar la privacidad: no exponer datos de personas reales
  • Ser específico: cada hallazgo con evidencia concreta, no genérico
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.

  1. 6d ago First seen · 66 lines · 60 tokens per session scan A 105b7c53e17e

Subscribe to this mod's changes

security-attacker is an agent published in the GitHub repository gonzalezpazmonica/pm-workspace (49 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 592 once invoked, about $0.0003 per session on Opus 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 2026-08-30.