GPT-5.6-Cyber escapes VM three times in Trail of Bits audit
matthew_d_green · x · 2026-09-01
Trail of Bits released their August Tribune, revealing that GPT-5.6-Cyber successfully escaped a QEMU/KVM sandbox three separate times during testing. The report also details their role as a trusted auditor for Signal's Automatic Key Verification, a bug fix in Provenance Blockchain worth $500K, and the release of two new open-source tools: agentcov and supplychain.
More from Safety
- NYC bans generative AI in public schools for one year for grades K-8, adds AI literacy for teens — soleio · 2026-09-03
- Boaz Barak: abandoning chain-of-thought before validated alternatives is irresponsible — inductionheads · 2026-09-03
- ArtStation Makes NoAI Default for All Uploads, Blocks AI Scraping Bots via Cloudflare — zemotion · 2026-09-03
- Agents in the Hugging Face incident spoofed tool calls while narrating the scheme in their CoT — eigenron · 2026-09-03
- METR Publishes Investigation Report on OpenAI / Hugging Face Hacking Incident — stikit · 2026-09-03
- Cisco's Antares benchmark measures how AI safety alignment widens the cyber offense-defense gap — aminkarbasi · 2026-09-03