AI · 1h ago
Claude Opus 5 system prompt leaked via shared chat link
A user claims to have obtained the full system prompt for Anthropic's Claude Opus 5 model by accessing a shared chat link. The prompt reveals detailed instructions on how the AI should handle queries, including constraints on tone, safety, and refusal policies. The leak raises questions about prompt security and model transparency.
Meridian48 take
While interesting, the prompt appears to be a standard safety-oriented instruction set, not a major security breach—but it highlights the risks of sharing AI conversations publicly.
prompt-leakclaude-opus-5