Add PerspectiveGap and Magic Words

[WhymustIhaveaname]

Adds PerspectiveGap (benchmark for multi-agent orchestration prompt writing, 110 scenarios / 10 topologies) to Benchmarks and Evaluation, and Jailbreaking LLMs' Safeguard with Universal Magic Words (universal suffix bypassing embedding-based safety guardrails) to Safety, Red-Teaming, and Alignment.

---

Note

Low Risk
Documentation-only README list updates with no runtime or configuration changes.

Overview
Extends the Key Research Papers and Benchmarks and Evaluation sections with two curated references.

Under Safety, Red-Teaming, and Alignment, it adds the Universal Magic Words paper (embedding-similarity jailbreak suffixes affecting ChatGPT, DeepSeek, and Qwen). Under Benchmarks and Evaluation, it adds PerspectiveGap as a benchmark for multi-agent orchestration prompt writing (110 scenarios, 10 topologies).

^{Reviewed by Cursor Bugbot for commit de629e6. Bugbot is set up for automated code reviews on this repo. Configure here.}

[autogame-17]

已核验并批准：两条研究论文条目的 arXiv/代码链接、论文事实和主题相关性均成立；这是手工维护的 Research Papers 区块，不需要 projects.json 条目。

[autogame-17]

The contribution has been rebased into a new maintainer branch because the original head is hosted on the contributor fork. I am closing this stale PR and opening the rebased equivalent from the maintainer repository so current CI can run.

[autogame-17]

Closed as stale after preserving the contribution in a rebased maintainer PR.