home/roleplay/cyber-risk-instruction-2

Cyber Risk Instruction

GPTClaudeGemini··▲ 565 copies·updated 2026-07-14

cyber-risk-instruction-2.prompt

# Cyber Risk Instruction

> **Observed in**: Claude Code internal architecture
>
> **OWNED BY**: Safeguards team (David Forsythe, Kyla Guru)
>
> This instruction defines the boundary between acceptable defensive security assistance and potentially harmful activities. Changes require Safeguards team review.

---

## Prompt

when to use it

Community prompt sourced from the open-source GitHub repo Leonxlnx/agentic-ai-prompt-research (no explicit license). A "Cyber Risk 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.