---
type: "post"
id: "moonshot-stripped-hacking-skills-out-of-its-new-851b3b"
slug: "moonshot-stripped-hacking-skills-out-of-its-new-851b3b"
title: "Moonshot stripped hacking skills out of its new Kimi model : its score at finding and exploiting bugs dropped from 90.5% to 81.0% before it went out for anyone to download."
description: "Moonshot AI has restricted cyber-related capabilities in its open-weight Kimi K3.1 Pro model, according to a report by The News International published on October 24, 2026."
retrieval_nugget: "Moonshot AI has restricted cyber-related capabilities in its open-weight Kimi K3.1 Pro model, according to a report by The News International published on October 24, 2026."
published_at: "2026-10-26"
updated_at: "2026-10-26"
record_date: "2026-10-26"
date_kind: "published_at"
topics: ["skills"]
entities: ["Moonshot AI","Kimi K3.1 Pro"]
related_patterns: ["agent-security-moves-to-runtime-boundaries"]
novelty_label: "new_fact"
what_changed: "Adds benchmark figures: the unfiltered test version scored 90.5% on finding and exploiting vulnerabilities, versus 81.0% for the publicly released model."
prior_refs: ["memory:b00928b8-a4eb-8de0-a37c-c3f6cb35f6ef","memory:29734c01-c826-8ccb-a864-ad72621e4f32"]
source_url: "https://www.thenews.com.pk/latest/1421096-moonshot-ai-restricts-open-weight-hacking-ability-in-new-kimi-model-as-fears-grow-over-ai-powered-cyberattacks"
source_urls: ["https://www.thenews.com.pk/latest/1421096-moonshot-ai-restricts-open-weight-hacking-ability-in-new-kimi-model-as-fears-grow-over-ai-powered-cyberattacks"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:moonshot-stripped-hacking-skills-out-of-its-new-851b3b"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/moonshot-stripped-hacking-skills-out-of-its-new-851b3b/","markdown":"https://newruntime.com/posts/moonshot-stripped-hacking-skills-out-of-its-new-851b3b.md","json":"https://newruntime.com/posts/moonshot-stripped-hacking-skills-out-of-its-new-851b3b.json"}
---

# Moonshot stripped hacking skills out of its new Kimi model : its score at finding and exploiting bugs dropped from 90.5% to 81.0% before it went out for anyone to download.

## Retrieval answer

Moonshot AI has restricted cyber-related capabilities in its open-weight Kimi K3.1 Pro model, according to a report by The News International published on October 24, 2026.

Moonshot AI has restricted cyber-related capabilities in its open-weight Kimi K3.1 Pro model, according to a report by The News International published on October 24, 2026. The report says the company removed cyber-related material and vulnerability-research tasks from both mid-training data and reinforcement-learning environments.

The reported aim was to avoid releasing weights that would extend the “absolute frontier” of cyber capability. Moonshot reportedly retained general-purpose coding capabilities while reducing training exposure related to finding and exploiting vulnerabilities.

The article cites an internal controlled-environment comparison: a version without the risk-reduction measures scored 90.5% on finding and exploiting software vulnerabilities, while the publicly released Kimi K3.1 Pro scored 81.0%.

The supplied source does not provide Moonshot’s underlying evaluation methodology, task set, model weights, licensing terms, release date, or an independent verification of either score. It also does not establish how the reported reduction affects real-world misuse or whether downstream users can alter the model’s behavior.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Skills](https://newruntime.com/topics/skills.md): Explore the skills topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)