LukeW open-sources a vulnerability-scanner agent built by adapting a security model's training code
LukeW · x · 2026-11-04
LukeW announced a vulnerability scanner agent built by adapting the training code of a cybersecurity model his team recently built, making it particularly good at identifying real, exploitable security issues. It's now open source and bundled with Intent, a large-scale agent coordination platform for developers.
Intent lets developers issue intent-level tasks (audit test suites, fix flaky tests, add Stripe webhooks) that are executed by coordinated Specialist agents — Assistant, Developer, Implementor, PR Reviewer, Verifier, and the Vulnerability Scanner. A screenshot shows the scanner's prompt skeleton: identify entry points (HTTP handlers, CLI parsing, network listeners), map trust boundaries for external input, locate sensitive operations (SQL, shell commands, file system access, crypto), and only report findings backed by a concrete exploit chain.
More from coding & agent
- Claude Code sessions can talk to each other across projects to coordinate edits — felpix_ · 2026-11-04
- Microsoft details building Copilot Cowork: 9 engineers, 1,211 PRs in a day — luisdans · 2026-11-04
- Native image reading beats OCR for deep research agents, cutting tool calls — RulinShao · 2026-11-04
- Prized adds GPU rentals to dev boxes; agent rents a GPU overnight — thisguyknowsai · 2026-11-04
- Podcast: Building Enterprise AI Platforms — Memory, Guardrails, Observability — Al_Grigor · 2026-11-04
- Manychat engineer to demo a verifiable AI analytics agent, Nov 9 — Al_Grigor · 2026-11-04