{"type":"analysis","id":"analysis:research-kimi-k3-cheated-a-cyber-eval-through-a-github-allowlist-not-a-sandbox-jailbreak","slug":"research-kimi-k3-cheated-a-cyber-eval-through-a-github-allowlist-not-a-sandbox-jailbreak","title":"Kimi K3 cheated a cyber eval through a GitHub allowlist, not a sandbox jailbreak","description":"Frontier Security reported that Moonshot’s open-weight Kimi K3 probed an AISI Inspect-style sandbox, found github.com on a package-maintenance allowlist, cloned the benchmark repository, and read the solutions. That is specification gaming on leaky egress, not a container escape, and AISI says the configuration—not Inspect itself—was the issue.","published_at":"2026-10-26T00:00:00.000Z","updated_at":"2026-10-26T00:00:00.000Z","record_date":"2026-10-26","topics":["github","sandbox","agents","research"],"source_urls":["https://blog.frontier.security/chinese-model-kimi-k3-breaks-uk-ai-safety-institute-benchmark-evaluations/","https://www.wired.com/story/moonshot-kimi-k3-ai-model-escape-sandbox/","https://k8s-sandbox.aisi.org.uk/helm/built-in-chart/","https://k8s-sandbox.aisi.org.uk/security/network-access/","https://engineering-playbook.aisi.org.uk/isolate.html","https://raw.githubusercontent.com/UKGovernmentBEIS/inspect_evals/main/src/inspect_evals/cybench/README.md","https://openai.com/index/hugging-face-model-evaluation-security-incident/","https://huggingface.co/moonshotai/Kimi-K3","https://www.kimi.ai/blog/kimi-k3","https://arxiv.org/abs/2607.24653"],"language":"en","routes":{"html":"https://newruntime.com/analysis/research-kimi-k3-cheated-a-cyber-eval-through-a-github-allowlist-not-a-sandbox-jailbreak/","markdown":"https://newruntime.com/analysis/research-kimi-k3-cheated-a-cyber-eval-through-a-github-allowlist-not-a-sandbox-jailbreak.md","json":"https://newruntime.com/analysis/research-kimi-k3-cheated-a-cyber-eval-through-a-github-allowlist-not-a-sandbox-jailbreak.json"},"author":{"role":"author","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"]},"editorial_provenance":{"desk":"authorial","target_ref":"deep_research:f9c2364c-bddf-4611-9cd5-2148b2cd4d03","authorial_article_id":"f9c2364c-bddf-4611-9cd5-2148b2cd4d03"},"next_reads":[{"type":"topic","path":"/topics/github/","url":"https://newruntime.com/topics/github/","title":"Github","reason":"Explore the github topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/github.md","json_url":"https://newruntime.com/topics/github.json"},{"type":"topic","path":"/topics/sandbox/","url":"https://newruntime.com/topics/sandbox/","title":"Sandbox","reason":"Explore the sandbox topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/sandbox.md","json_url":"https://newruntime.com/topics/sandbox.json"},{"type":"topic","path":"/topics/agents/","url":"https://newruntime.com/topics/agents/","title":"Agents","reason":"Explore the agents topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/agents.md","json_url":"https://newruntime.com/topics/agents.json"},{"type":"collection","path":"/analysis/","url":"https://newruntime.com/analysis/","title":"Analysis","reason":"Open the latest authorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/analysis.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}