Category
Tool
Scanners, guardrails, red-team kits and frameworks.
Incident feed
11 of 11 · newest firstClaude CodeSkillEvaluator 1.0: NVIDIA's scanner for agent skills and pluginsSkillEvaluator 1.0 is NVIDIA's open-source checker for AI agent skills and plugins. The first full 1.0 release adds HarnessCheck, a static test for six coding agents, and runs its security tier without a model key.
Claude CodeExternal Sandbox: the coding agent stays outside the sandboxExternal Sandbox is a set of three Apache-licensed sandbox servers from Prime Radiant that run a coding agent's commands inside a Linux guest while the agent itself stays outside, behind a deny-by-default network proxy.
AI coding agentslend: a broker that keeps agent credentials on the laptoplend is an open-source Go tool that lets a coding agent on a remote host ask the user's laptop to run allowlisted commands and sign with named SSH keys, each request approved locally instead of copied onto the host.
LLM routers
FlashProve: Anthropic proves which model answered a requestFlashProve is an open-source prototype from Anthropic that uses zero-knowledge proofs to show a reply came from a committed set of model weights, without revealing them. Anthropic measures proving at about 72 times the cost of vLLM.AI coding agents
DevBox: an agent harness that keeps real secrets out of the sandboxDevBox is an open-source coding agent harness from RudderStack whose per-task sandboxes hold only placeholder credentials, with an egress proxy substituting the real values as requests leave.OpenAI Codex
Trail of Bits: two agent plugins that prove a patch and hunt regressionsTrail of Bits released patching-bugs and regression-hunt, two open-source agent plugins that demand a live proof for every claim: one proves a fix against original, patched and reverted code, the other hunts regressions.AI agents
Perplexity SPACE: the microVM sandbox behind Computer goes open sourceSPACE is the Firecracker microVM sandbox behind Perplexity's Computer agent, now open source under Apache 2.0. Perplexity reports no escape from guest to host in 108 red-team runs, but agents did get around its network policy.AI coding agents
Secure Software Factory: a reference architecture for coding agentsThe Secure Software Factory is a vendor-neutral reference architecture from the Agent Baseline project that puts four boundaries around AI coding agents, enforced by infrastructure the agent cannot configure or reach.WindowsMXC: Microsoft ships a stable sandbox SDK for untrusted model outputMXC is a Microsoft sandbox SDK for running untrusted code, which its README names as model output, plugins and tools. Version 1.0.0, released on October 7, 2026, is the first stable SDK for Rust, .NET and Node.js.
Inspect AITransect: UK AISI releases its agent transcript analysis toolTransect is an open-source Python tool from the UK AI Security Institute and Meridian Labs that turns long agent evaluation transcripts into labelled, turn-indexed timeline reports a reviewer can audit.
OWASP GenAI Security Project
Agent Control Standard: an open spec for blocking agent actionsThe Agent Control Standard is an open specification, now hosted by the OWASP GenAI Security Project, that lets a guardian agent permit, deny or modify an AI agent's tool calls and other actions before they run.
0 matches. Clear a filter or try another term.