claude

custom-plugin-ai-red-teaming

AI Red Teaming Plugin Development

5 on GitHubupdated 10 months ago

Not in a marketplace yet, so it loads for one session with --plugin-dir.

Plugin custom-plugin-ai-red-teaming in pluginagentmarketplace/custom-plugin-ai-red-teaming. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (25)

  • adversarial-examples
  • adversarial-training
  • automated-testing
  • benchmark-datasets
  • certifications-training
  • code-injection
  • continuous-monitoring
  • data-poisoning
  • defense-implementation
  • infrastructure-security
  • input-output-guardrails
  • llm-jailbreaking
  • model-extraction
  • model-inversion
  • prompt-hacking
  • prompt-injection
  • rag-exploitation
  • red-team-frameworks
  • red-team-reporting
  • responsible-disclosure
  • safety-filter-bypass
  • secure-deployment
  • security-testing
  • testing-methodologies
  • vulnerability-discovery

Slash commands (4)

  • /custom-plugin-ai-red-teaming:attack
  • /custom-plugin-ai-red-teaming:defend
  • /custom-plugin-ai-red-teaming:report
  • /custom-plugin-ai-red-teaming:test

Subagents (8)

  • 01-red-team-commander
  • 02-prompt-injection-specialist
  • 03-adversarial-input-engineer
  • 04-llm-vulnerability-analyst
  • 05-defense-strategy-developer
  • 06-api-security-tester
  • 07-compliance-audit-specialist
  • 08-ai-security-automation
View source on GitHub

Problems found in this repo's manifests

  • .claude-plugin/marketplace.json is not valid JSON

Maintain custom-plugin-ai-red-teaming?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted