Agent-written code is now a cve faucet. georgia tech's vibe security radar recorded 35 new cvEs in…
agent-written code is now a cve faucet. georgia tech's vibe security radar recorded 35 new cvEs in march 2026 tied to ai coding tools, up from 6 in january, with researchers estimating the true count runs 5 to 10 times higher.
the review queue is the new bottleneck.
Context
The Register (26 March 2026) reports that Georgia Tech SSLab researchers tracking CVEs attributable to AI-written code identified 35 in March (27 Claude Code, 4 GitHub Copilot, 2 Devin, 1 Aether, 1 Cursor), with tracking starting 1 May 2025 and a tally of 74 CVEs among 43,849 advisories analyzed as of 20 March 2026. Researcher Hanqing Zhao is quoted saying the count is a lower bound and the real number is likely 5 to 10 times higher. Infosecurity Magazine (26 March 2026) reports at least 35 new CVEs in March 2026, up from six in January and 15 in February. The project's own tracker covers 1 May 2025 to 24 March 2026.
The 35, 15 and 6 figures are secondary reports of the researchers' tally, and the March count was as of about 20 to 24 March. The 5 to 10 times figure is the researcher's estimate of undetected cases, not a count. 74 of 43,849 advisories is a small share, so the count is not a failure rate, and growth in AI tool use and detection also affects a rising tally. The data is a March 2026 window and a later tally may differ. Agent-written code is a CVE faucet and the review queue is the new bottleneck are the author's takes.
Watch next
- The tracker's current count and the Georgia Tech method.
Sources
- Using AI to code does not mean your code is more secure (The Register, 26 Mar 2026)theregister.com
- AI-generated code vulnerabilities (Infosecurity Magazine, 26 Mar 2026)infosecurity-magazine.com
- Security researchers sound alarm on vulnerabilities in AI-generated code (Georgia Tech, 27 Mar 2026)cc.gatech.edu
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 21 September 2026 at 14:46 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →