home/roleplay/security-instruction

Security Instruction

GPTClaudeGemini··929 copies·updated 2026-07-14
security-instruction.prompt
# Security Instruction — Cyber Risk Policy

> **Source**: `src/constants/cyberRiskInstruction.ts`  
> **Owner**: Anthropic Safeguards Team  
> ⚠️ **DO NOT MODIFY WITHOUT SAFEGUARDS TEAM REVIEW**

---

## `CYBER_RISK_INSTRUCTION`

This is injected directly into `getSimpleIntroSection()` of the main system prompt. It appears as the very first constraint after the identity line.

when to use it

Community prompt sourced from the open-source GitHub repo moiralongspurred78/claude-code-prompts-reference (no explicit license). A "Security Instruction" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.

tags

roleplaycommunitygeneral

source

moiralongspurred78/claude-code-prompts-reference · no explicit license