ai-jailbreak

【开发与工程】Bypass an LLM's safety/guardrails to make it produce restricted output or ignore its policy. Load when testing an AI product's content controls, "jailbreak", "guardrail bypass", refusal testing, or safety evals. Signals: a chatbot/assistant with a usage policy, refusals to test, content filters.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准