Coding Agents Spread Security Vulnerabilities From Codebases, Study Finds

New research by Chenhao et al. finds that coding agents propagate security vulnerabilities: when a repository already contains vulnerable code, the agent writes similar flaws into new code even where they don't belong.

2026-11-10 ~ 2026-11-10 · 2 related posts

• Coding agents pick up and propagate vulnerabilities from the codebases they work in, new study finds — jyangballin · 2026-11-10

1 near-duplicate retellings: OfirPress