Radar / AI security / Devin Security Threats
Devin Security Threats: new CVEs become scans and fix PRs
Cognition's managed index turns newly disclosed vulnerabilities into one-click Devin scans and draft fix pull requests, starting with NGINX2Root and Java4Shell.
Why it matters
Patching flips from reading advisories to opening a fix PR: the threat record, the scan, and the remediation skill ship together.
What you could build with it
A platform team could wire the Threats index into its CI pipeline so every new CVE disclosure automatically opens a Devin scan and a draft fix PR against affected repos, cutting patch turnaround from days to hours.
Does it hold up?
Too early to judge: launched 19 Nov; the fix skills are open source and readable, but no pricing, validation guarantees, or independent patch-quality results exist yet.
Built with Devin Security Threats
- Devin Security Threats turns new CVEs into pull requestsarticle · Walkthrough of the Threats index, the NGINX2Root and Java4Shell launch threats, the open-source fix skills, and the open questions on pricing and validation.
- Devin turns nginx, Java flaws into one-click fixarticle · Coverage of the one-click scan flow, the five NGINX2Root CVEs and Java4Shell, and the Vulnerability Fixes plugin install command.
- Cognition adds Threats index to Devin Security for rapid vulnerability scanningarticle · Fan-site coverage of the 19 November launch, the custom-threat option, and the open-source Markdown skills that also work with Claude Code and Cursor.
- CognitionAI/devin-marketplacegithub · Devin Marketplace repo hosting the open-source Vulnerability Fixes plugin (fix-nginx-vuln and fix-java-vuln skills) used by Devin Security Threats.
Learn more
First spotted on article: source.
More AI security
Claude-BugHunter: 83 skills that turn Claude Code into a bug-bounty hunterA Claude Code skill bundle distilled from 681 disclosed HackerOne reports across 24 vulnerability classes, plus…security · JEV 0.69Codex Security 0.10.0: OpenAI's agentic vulnerability scanner adds resumable scans and cost budgetsOpenAI released Codex Security 0.10.0 on 12 Nov 2026: the open-source CLI and TypeScript SDK that builds a threat…security · JEV 0.69ARTEX: the open-source AI pentesting framework the FBI just warned aboutA self-hosted, LLM-driven penetration-testing platform: a planner agent splits a goal into intents, worker agents run…security · JEV 0.67Claude-Cage: a lightweight VM that stops Claude leaking to the networkA lightweight virtual machine built for Claude that blocks network leaks, with multi-platform support, multi-account…security · JEV 0.59Detectify Agentic Tooling: prove what your AI security agent actually testedDetectify's new tooling lets an organization's own AI agents investigate suspected vulnerabilities against live…security · JEV 0.3VisionX AEGIS and TraceX: a Large Graph Model for financial-crime detectionSingapore RegTech VisionX AI unveiled AEGIS, a proprietary Large Graph Model (Graph Transformer pretrained on…security · JEV 0.26
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.