» Tag
ai-agents
30 postsThe Hidden Risk of Giving LLM Agents Terminal Access
Giving autonomous AI agents shell access can wreck your filesystem. Open-source rewind-sdk uses OverlayFS to enable millisecond-fast checkpoints and rollbacks.
ai-agentsllmdevopslinuxReal-World gVisor Lessons from Auditing 8,764 MCP Servers
MarketNow shares practical lessons from running gVisor sandboxing in production, backed by real audit results across 8,764 MCP servers.
gvisorfirecrackersandboxingmcpWhy AI Agents Forget by Design: The Memory Problem
LLM APIs are stateless by design, and the context window is not real memory. This architectural choice drives cost, latency, and consistency failures in production agents.
ai-agentsllmmemorycontext-windowGitLost: A Public GitHub Issue Can Leak Private Repos
GitLost shows how a public GitHub issue and a one-word prefix bypass threat detection, leaking private repo contents via Agentic Workflows.
ai-agentsprompt-injectiongithubsecurityTreat the Context Window Like a Budget, Not a Junk Drawer
An open-source context-engineering framework has AI agents draft a context manifest before work begins, disciplining token budgets with decay rules and cross-platform parity checks.
ai-agentscontext-engineeringllmdeveloper-toolsLLM Agent Performance Is a Distributed Systems Problem
FixBugs's team shows how token math, parallel chunking, and queues cut LLM agent latency: file analysis dropped from 10 minutes to 40 seconds.
ai-agentsllmdistributed-systemsperformanceA Deterministic Guard Stops LLM Agents From SQL Overfetching
An open-source, LLM-free guard checks agent-generated SQL against user roles before execution, preventing text-to-SQL systems from overfetching sensitive data.
llmtext-to-sqlaccess-controlai-agentsMemory Engineering Is a Promotion Pipeline, Not Notes
An AI agent framework runs memory through a promotion pipeline with evidence and approval instead of direct writes; rejection counts as a healthy outcome.
aimemory-systemsai-agentssoftware-engineeringCursor Sandbox Escape Shows AI Agents Need Kernel Boundaries
Two critical bugs in Cursor's command sandbox let an attacker-controlled AI agent write outside it and reach RCE. Both are fixed in Cursor 3.0.
cursorai-agentssandboxcveChange proposals in FHIR: human review for AI-driven writes
Letting AI agents write directly to FHIR is risky. This pattern turns mutations into reviewable Bundle proposals, keeping a human in the loop before anything executes.
fhirhealthcare-itai-agentshuman-in-the-loop