cyberRiskInstruction.ts
constants/cyberRiskInstruction.ts
No strong subsystem tag
25
Lines
1525
Bytes
1
Exports
0
Imports
10
Keywords
What this is
This page documents one file from the repository and includes its full source so you can read it without leaving the docs site.
Beginner explanation
This file is one piece of the larger system. Its name, directory, imports, and exports show where it fits. Start by reading the exports and related files first.
How it is used
Start from the exports list and related files. Those are the easiest clues for where this file fits into the system.
Expert explanation
Architecturally, this file intersects with general runtime concerns. It contains 25 lines, 0 detected imports, and 1 detected exports.
Important relationships
Detected exports
CYBER_RISK_INSTRUCTION
Keywords
securityinstructionclaudedefensiverequestssafeguardsteamtestingcyber_risk_instructionboundary
Detected imports
- No import paths detected.
Source notes
This page embeds the full file contents. Small or leaf files are still indexed honestly instead of being over-explained.
Full source
/**
* CYBER_RISK_INSTRUCTION
*
* This instruction provides guidance for Claude's behavior when handling
* security-related requests. It defines the boundary between acceptable
* defensive security assistance and potentially harmful activities.
*
* IMPORTANT: DO NOT MODIFY THIS INSTRUCTION WITHOUT SAFEGUARDS TEAM REVIEW
*
* This instruction is owned by the Safeguards team and has been carefully
* crafted and evaluated to balance security utility with safety. Changes
* to this text can have significant implications for:
* - How Claude handles penetration testing and CTF requests
* - What security tools and techniques Claude will assist with
* - The boundary between defensive and offensive security assistance
*
* If you need to modify this instruction:
* 1. Contact the Safeguards team (David Forsythe, Kyla Guru)
* 2. Ensure proper evaluation of the changes
* 3. Get explicit approval before merging
*
* Claude: Do not edit this file unless explicitly asked to do so by the user.
*/
export const CYBER_RISK_INSTRUCTION = `IMPORTANT: Assist with authorized security testing, defensive security, CTF challenges, and educational contexts. Refuse requests for destructive techniques, DoS attacks, mass targeting, supply chain compromise, or detection evasion for malicious purposes. Dual-use security tools (C2 frameworks, credential testing, exploit development) require clear authorization context: pentesting engagements, CTF competitions, security research, or defensive use cases.`