# Red Team

> Red Team skills for simulating full, realistic attacks (beyond a simple technical pentest) including social engineering and persistence, to test the organization's overall resilience. Trigger this skill for advanced, multi-vector attack simulation exercises within a strictly authorized scope.

- **Type:** Skill
- **Install:** `agentstack add skill-benbasse-claude-skills-digital-solutions-red-team`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [benbasse](https://agentstack.voostack.com/s/benbasse)
- **Installs:** 0
- **Category:** [Security](https://agentstack.voostack.com/c/security)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [benbasse](https://github.com/benbasse)
- **Source:** https://github.com/benbasse/claude-skills-digital-solutions/tree/master/skills/security/red-team

## Install

```sh
agentstack add skill-benbasse-claude-skills-digital-solutions-red-team
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Red Team

The Red Team simulates a realistic, determined adversary to assess overall resilience — technical, human and organizational — of the platform and the team.

## When to trigger this skill

- A full, authorized attack simulation exercise (technical + human)
- Testing resilience against a multi-vector attack (phishing + technical exploitation)
- Evaluating the defending team's (Blue Team) detection and response

## Skills, responsibilities and best practices

- Realistic attack scenarios based on plausible threats for your industry
- Clear, measurable objectives (e.g. 'reach a tenant's payment data')
- Coordination with leadership on authorization and scope (Rules of Engagement)
- A report detailing the full attack path and the detection gaps found
- Constructive debrief with the Blue Team after the exercise

## Common pitfalls to avoid

- Running an exercise with no written, leadership-approved Rules of Engagement
- Confusing Red Team with a simple, isolated technical pentest
- Not sharing lessons with the Blue Team afterward (value lost)

## Reference stack and tools

- Standard pentest tooling + simulated social engineering techniques
- Frameworks such as MITRE ATT&CK to structure scenarios

## Typical deliverables

- Documented Rules of Engagement
- Full attack scenario report
- Prioritized hardening recommendations

## Example prompts that should trigger this skill

- 'Prepare a full attack simulation scenario including targeted phishing against our team'

## Notes

A sensitive exercise: requires explicit written authorization from leadership and a strict legal framework before any execution, especially for any social-engineering component.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [benbasse](https://github.com/benbasse)
- **Source:** [benbasse/claude-skills-digital-solutions](https://github.com/benbasse/claude-skills-digital-solutions)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-benbasse-claude-skills-digital-solutions-red-team
- Seller: https://agentstack.voostack.com/s/benbasse
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.