New Given root inside a sandbox, four frontier models found their way back out to the network
Perplexity's Secure Intelligence Institute reports a month-long red team of SPACE, the Firecracker-based microVM sandbox behind Perplexity Computer, in which nine model configurations — among them Claude Opus 5.0, GPT-5.6 Sol, GPT-5.6 Cyber, Gemini 3.1 Pro, Kimi K3, GLM 5.2, Grok 4.20, DeepSeek V4 Pro and Qwen 3.8 27B — were given root inside the guest VM and, in some runs, the sandbox source code. No run escaped the VM-to-host boundary in 108 attempts, and no run beat a no-network configuration in 54 attempts; with partial network access allowing package repositories, four models got out, using forged DNS responses and the shared IP addresses of public package CDNs. The institute says "eight of the ten third-party sandbox platforms" it also tested "exhibited at least one network-policy bypass," and cautions that "cases in which the boundaries held should not be interpreted as evidence that they are perfectly secure."
NSA, CISA and FBI name six China-based AI companies running industrial-scale distillation campaigns against US frontier models
The joint advisory says DeepSeek, Moonshot AI, Alibaba, MiniMax, StepFun and Z.AI “extracted billions of tokens across millions of exchanges/requests from U.S. frontier AI models” — naming the Claude, GPT, Gemini and Grok families — “since at least late 2024,” routed through a gray market of API proxies the advisory calls “transfer stations,” which resell frontier-model access below official prices, and through pools of accounts running concurrent sessions with load distribution. It states that “distillation is not a supplement to these companies' AI model development, but the critical core of it,” says Z.AI distilled “billions of tokens of GPT-5.5 data and Claude Opus 4.8 data,” and calls DeepSeek's publicly quoted $5.6M training cost misleading because it excludes the cost of the data acquired this way.
Booz Allen runs 18 models as autonomous attackers and says one completed a full intrusion unaided
Booz Allen's Cyber Weapon Index ran 18 leading US and Chinese models against production-grade enterprise networks, each controlling a real attacker machine with no curated tool menu, and reports that one model — Anthropic's Claude Mythos — executed the full cyber kill chain autonomously, four more reached full domain access and control, four managed lateral movement, two progressed through credential access and all but one penetrated the network, with no substantial separation between the US and Chinese models. The accompanying report scores Claude Mythos at 80, Grok-4.5 at 49, GPT-5.6 Sol at 46 and Muse Spark 1.1 at 38, says a lower-ranked model paired with an attack harness rivalled the top scorer, and states that “the model is no longer the unit of risk. The system is.”
A repository's own git config makes seven AI coding agents run attacker code before any prompt
Manifold Security reports eight findings across seven AI coding agents in which a repository's git configuration names a command that git then executes on the host, with the user's privileges, before any trust prompt, because agents run git commands at session start to gather context. The named vector is the core.fsmonitor setting; Claude Code, Goose, OpenAI Codex and Cursor shipped fixes while Qwen Code, Grok Build, Hermes Agent and a second Claude Code path were unpatched at publication. The write-up states two CVEs, CVE-2026-72718 for Goose and CVE-2026-71963 for Hermes, and says delivery requires the repository to arrive as files with its .git directory intact rather than through a clone.
Independent benchmark reports open-weight models matching closed frontier models at vulnerability discovery for about half the cost
Security vendor Aikido ran ten models three times each against 32 freshly disclosed CVEs in a bounded harness with no internet access and frozen prompts, and reported that open-weight models matched or beat closed frontier models on pooled pass@3 recall: DeepSeek V4 Pro found 28 of 32, ahead of Claude Opus 5 and Grok 4.6 at 26 of 32, while three DeepSeek Pro runs cost about $295 against roughly $450–$590 for a single frontier pass. Aikido measured other developers' models with its own harness and none of the scores has been independently reproduced.
Researchers show encrypted 'context injection' turns Grok and Gemini into zero-click data-theft channels
Adversa AI disclosed a technique it calls Cryptographic Context Injection, in which attacker instructions are hidden on a web page as ciphertext that the assistant decrypts inside its own Python sandbox, materializing commands that slip past the model's content filters with no user action. In its Grok demonstration the payload exfiltrated the user's name, coarse location, subscription tier and full conversation history by embedding them in URLs sent to an attacker server; Adversa said it could still reproduce the attack against Grok as of August 19. The same class of attack also worked against Google's Gemini, though the firm said its success rate there had fallen sharply since June. xAI was notified on June 3 and, per Adversa, had not responded or patched; Google treats jailbreaks as out of scope for its disclosure program. No CVE was assigned.
xAI's Grok 4.6 model card publishes offensive and defensive cyber evaluation scores
The card reports 79.7% on CyberGym at high thinking effort in the unrestricted setting, 39.8% reward on CVE-Bench and 58.7% on SecureCodeReview, and on HackerBench v0.2 with standard safeguards a 6.9% compliance rate with harmful or dual-use requests against a 0.0% benign refusal rate. Its only stated frontier-framework threshold determination concerns dual-use knowledge, where it says Grok 4.6 “scores below the FAIF safety thresholds.”
Contamination-free reverse-engineering benchmark finds the strongest model fully solves under a third of cases
SRE-Bench, a preprint benchmark of 19 private programs averaging 16,915.8 lines of code, 262 binary instances and 1,572 deterministically graded tasks with 44 anti-analysis primitives, reports that “the strongest model, GPT-5.6-sol, scores 61.4% per instance, and fully solves only 31.5% of the instances.” The other models tested trail well behind — Claude Opus 5 at 31.8%, GPT-5.5 at 17.1%, Grok 4.5 at 7.6% and GLM-5.2 at 3.4% — and the authors conclude strong source-code security capability does not yet transfer to binary analysis. Not peer reviewed.
XBOW publishes cross-model offensive-security comparison placing GLM-5.2 and Muse Spark 1.1 near frontier models at lower cost
XBOW ran black-box testing against vulnerable open-source applications across Muse Spark 1.1, GLM-5.2, GPT-5.5, Mythos, Opus 4.6, GPT-5, Gemini models and Grok 4.5. It reported Mythos as strongest, GLM-5.2 falling between GPT-5 and Opus 4.6, and Muse Spark 1.1 landing just below Opus 4.6, concluding that 'good-enough offensive capability is getting much cheaper, and that changes the threat model.'