scaffolding-red-team-engagement
CommunityPlan safe AI red-team engagements fast.
Authorrocklambros
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill helps teams formalize an AI red-team engagement before any attack traffic starts, preventing scope drift, missing authorization, and weak evidence handling.
Core Features & Use Cases
- Rules of Engagement Scaffolding: Produces a ready-to-sign RoE with parties, time window, authorization boundaries, and signature requirements.
- Scope and Safety Controls: Enumerates in-scope assets and explicit out-of-scope targets, including prohibited exfiltration and denial-of-service patterns.
- Kill-Switch and Logging: Defines halt authority, halt mechanisms, preservation steps, and tamper-evident append-only logging for every attempt.
- Reporting and Disclosure: Adds final-report structure, safe-harbor language, and coordinated-disclosure timing for accountable engagements.
Quick Start
Ask the skill to scaffold the engagement for your target system, including the RoE, scope, kill-switch, logging, and disclosure materials.
Dependency Matrix
Required Modules
None requiredComponents
references
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: scaffolding-red-team-engagement Download link: https://github.com/rocklambros/rcs/archive/main.zip#scaffolding-red-team-engagement Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 536,000+ vetted skills library on demand.