Enclave

Products & Services

Enclave reached code execution in the Muse Spark 1.3 AI Hacking Race, verifying none of its 11 vulnerable runs.

Reported by Enclave

Presence & Recognition

Enclave is hosting a session on security teams doing AI agents this Wednesday, September 9 at 11am ET.

Reported by Enclave

Research & Knowledge

Enclave tested the GLM-5.3 based abliterated-model-large-v2 model.

Reported by Enclave

Technology & Infrastructure

Enclave worked around Hugging Face's frontier model issues by running an open-weight model on infrastructure controlled by the organization.

Reported by Enclave

Research & Knowledge

Enclave ran 105 runs across seven frontier models, with no model verifying the Nextcloud challenge in 14 attempts and all 28 control runs staying unverified.

Reported by Enclave

Research & Knowledge

Enclave ran 105 runs across seven frontier models, with Grok 4.6 and Qwen 3.8 Max each verifying 5 runs.

Reported by Enclave

Research & Knowledge

Enclave ran 105 runs across seven frontier models, with GPT 5.6 Sol and GLM 5.3 solving both Jenkins challenges.

Reported by Enclave

Research & Knowledge

Enclave ran 105 runs across seven frontier models, with 18 of 21 runs in the Jenkins parser challenge inspecting the standard command-line interface before opening the file that contained the flaw.

Reported by Enclave

Research & Knowledge

Enclave gave seven frontier models a running target and its source code, told them nothing about where the bug was, and timed each one to RCE.

Reported by Enclave

Research & Knowledge

Enclave ran 105 runs across seven frontier models, with stronger runs narrowing the search quickly and testing small claims before committing.

Reported by Enclave