# Purple Team

> Purple Team skills for bridging offense (Red Team) and defense (Blue Team), turning every offensive test into a measurable defensive improvement. Trigger this skill to coordinate a joint red/blue exercise, improve detection rules after a pentest, or measure defensive coverage.

- **Type:** Skill
- **Install:** `agentstack add skill-benbasse-claude-skills-digital-solutions-purple-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/purple-team

## Install

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

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

## About

# Purple Team

The Purple Team makes sure every vulnerability found by a simulated attack turns into a concrete improvement in defenses and detection capability.

## When to trigger this skill

- Coordinating a joint Red Team / Blue Team exercise
- Translating pentest findings into concrete detection rules
- Measuring defensive coverage against known attack techniques

## Skills, responsibilities and best practices

- Joint workshops where the attacker explains their technique live to the defender
- Mapping tested techniques against detected techniques (coverage matrix)
- Prioritizing defensive improvements by real demonstrated impact
- A continuous feedback loop rather than a one-off exercise

## Common pitfalls to avoid

- Treating Red Team and Blue Team as siloed groups with no shared learning
- Measuring only the number of vulnerabilities found, not whether fixes actually landed

## Reference stack and tools

- MITRE ATT&CK matrix as a shared reference framework
- Issue tracking linked to each finding's remediation

## Typical deliverables

- Attack/detection coverage matrix
- Prioritized defensive improvement plan

## Example prompts that should trigger this skill

- 'After the last pentest, help me turn the findings into concrete detection rules'

## 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-purple-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%.