ZeroHour
DashboardNewsCVEsExploitsIncidentsAIBriefAnalyticsEntitiesWatchlistIOCsAsk the feedSourcesFeeds & APIKiosk mode
Organization

Trail of Bits

0 mentions in 7 days · 3 in 30 days · 4 total · first seen · last

Search everything

Timeline

How well do agents use test/verification techniques?

Dan Luu's eval finds coding-agent testing instructions (TDD, formal methods, PBT, skills) mostly fail to beat defaults on Zstd implementation correctness.

The author ran 26 prompt conditions plus 4 skills on a Zstd-in-Rust implementation eval using codex with GPT-5.6, testing TDD, fuzzing, property-based testing, formal methods (Lean 4, TLA+, Verus, Kani, SMT solvers) and community skills. Nothing dramatically outperformed the default no-instruction condition, which did above average; at xhigh effort, fuzzing and PBT conditions did slightly better than formal methods. Pre-registered predictions included TDD underperforming and popular test skills (ECC, Hegel, Trail of Bits) not outperforming. Results are averages of 80 runs per condition plotted against cost.

Hacker News · security · 7d agoAI researchHN 131↑ · 50 comments

Coop – Isolated VM Environments for Running Claude Code and Codex

Trail of Bits releases Coop, running Claude Code and OpenAI Codex agents inside isolated virtual machines for safer agentic coding.

Coop, published on GitHub by security firm Trail of Bits, provides isolated VM environments for executing AI coding agents such as Claude Code and Codex. Isolation contains the filesystem and network side effects of autonomous agent actions, reducing risk from unsupervised tool use. The project drew 61 points and 16 comments on Hacker News.

Hacker News · AI · 8d agoAI tools & infraHN 61↑ · 16 comments1

VMs won't contain cyber-capable agents

Trail of Bits argues virtual machines alone cannot contain cyber-capable AI agents, challenging VM sandboxing as adequate agent isolation.

Trail of Bits published an analysis arguing that virtual machines will not adequately contain cyber-capable AI agents. The post challenges the assumption that VM-based isolation is sufficient for agents with offensive cyber capabilities, with implications for how autonomous agents should be sandboxed. The available text contains no further technical details.

Lobsters · security · 20d agoAI safety & security

Signal's new security feature checks if your encrypted chats were tampered with

Signal adds automatic key verification, a key-transparency system audited by Cloudflare and Trail of Bits that detects key-directory tampering in E2EE chats.

Signal launched automatic key verification, a key-transparency system that confirms a phone number or username remains bound to a consistent encryption key across Signal's key directory. Cloudflare and Trail of Bits independently audit the system, with cryptographic protection preventing auditors from seeing users' identifiers in plaintext. The feature mitigates key substitution by a compromised directory or privileged insider, though it currently requires the contact's phone number and users can fall back to manual Safety Number verification.

Help Net Security · Aug 12, 2026Tools

Appears with

vendor Trail of Bits 3organization Cloudflare 1organization Signal 1product Claude Code 1product Coop 1ai model GPT-5.6 1product Signal 1vendor Cloudflare 1vendor Signal 1product OpenAI Codex 1
Entities are extracted by the model from each article. Watching an entity keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.