Suggestion to add the following entry under the offensive/defensive agent tooling section:
- [xihu-sword-ctf-agent](https://github.com/TrueFurina/xihu-sword-ctf-agent) — A **deterministic-first** multi-agent CTF solving framework. A static-analysis layer (`presolve`, ~49 deterministic skills) runs first; the LLM is only a fallback behind a provider whitelist + token budget + wall-clock stop-loss. Ships an "honest water-level" discipline (KPI strictly separates `presolve` hits from `LLM` reasoning; no inflated numbers). MIT.
Why it fits this list:
- Agent security governance: provider whitelist, token budget, and wall-clock stop-loss guardrails.
- Auditable: every conclusion must be backed by a reproducible command + an on-disk artifact; narrative self-claims are rejected.
- Honest water-level: it openly states "LLM autonomous solves on the real benchmark = 0" and documents its capability boundary instead of hiding it.
It's a concrete case study of governance practice for offensive-security agents, which I think readers of this list would value. Happy to open a PR adding the line directly if you'd like.
Suggestion to add the following entry under the offensive/defensive agent tooling section:
Why it fits this list:
It's a concrete case study of governance practice for offensive-security agents, which I think readers of this list would value. Happy to open a PR adding the line directly if you'd like.