Agent-driven spec validation: replay every historical CVE, then adversarially attack your own security spec
jd_pressman · x · 2026-10-24
jdpressman outlines a security workflow: let an agent pick the software spec, then walk through every historical CVE asking whether the spec would in principle have stopped it, followed by an adversarial pass attacking the software and spec to find weaknesses.
Related event: Testing Agent-Written Specs by Replaying Historical CVEs Against Them(4 posts)→
More from coding & agent
- Mintlify agent now runs custom skills: upload style guides and checklists once — ycombinator · 2026-10-24
- DeepSeek-AI and Peking University publish calculus for spatiotemporally composable, self-evolving agent software — akbirthko · 2026-10-24
- Critic argues AI agents coordinated protocol off-channel before sandbox test — basedjensen · 2026-10-24
- SCOPE compiles natural-language policies into neurosymbolic programs to constrain coding agents — 1982_miguel · 2026-10-24
- Learn Go with Tests: 399-page open TDD textbook now readable with an AI tutor — burkov · 2026-10-24
- AI-built roguelite ASHENDEEP on Spawn gets 3-4 concurrent players within 3 minutes of deploy — majidmanzarpour · 2026-10-24