9 stories tagged with #untrusted, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Untrusted"
Show HN: Noisegate – a differential-privacy gateway for untrusted AI agents
Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a formal guarantee no individual's recor…
Semantic transactions: securing untrusted AI agent workflows at the OS boundary
Trust the system, not the prompt: Securing untrusted LLM tools with transactional boundaries and effect outboxes.…
MSCI clock ticking on Indonesia’s broken and untrusted IDX
For decades, Indonesia Stock Exchange’s (IDX) institutional structure has acted as a brake on the growth and global competitiveness of Indonesia’s capital…
Show HN: A lightweight compiler for untrusted AI Agent scripts
The smart compiler and dumb VM architecture for ultimate performance.…
How to Run Untrusted AI Agent Code Without Docker
Docker shares the host kernel. That was always the trade. It was fine when a human read the script...…
Researchers urge treating AI agents as untrusted systems for crypto security
Researchers argue AI agents must be treated as untrusted systems with least-privilege sandboxing, citing a $500K crypto wallet exploit and risks to DeFi protocols.…
LLM's code is just untrusted text, until you validate it
The Linux Kernel Working On A Rust-Based Untrusted Data API
One of the newest interfaces being worked on for the Rust programming language support within the Linux kernel is an Untrusted Data API for data received into the kernel from user-…
RCE and arbitrary file write in Vitess vtbackup via untrusted MANIFEST fields
CVE-2026-27965 and CVE-2026-27969 - Vitess vtbackup trusted restore-time fields from the backup MANIFEST, allowing RCE via ExternalDecompressor and arbitrary path writes via FileEn…