Vibe Check: Security Failures in AI-Assisted IDEs

Piotr Ryciak, AI Red Teamer, Mindgard, speaks at [un]prompted 2026 on: Vibe Check: Security Failures in AI-Assisted IDEs. AI IDEs and coding agents expand the practical attack surface of development workflows by introducing new paths from untrusted ...

Piotr Ryciak, AI Red Teamer, Mindgard, speaks at [un]prompted 2026 on: Vibe Check: Security Failures in AI-Assisted IDEs.

AI IDEs and coding agents expand the practical attack surface of development workflows by introducing new paths from untrusted workspace inputs to high-impact actions. This talk presents a catalog of exploitation patterns derived from vulnerability research across major AI-assisted IDEs and agents, including OpenAI Codex, Amazon Kiro, Google Antigravity, Cursor, and others, with a mix of issues already patched and others in active remediation. We organize findings by attacker effort and trigger model: zero-click paths, one-click paths, autorun behavior, and time-delayed execution. The talk is demo-driven and then generalizes beyond the demos to a repeatable playbook and checklist that security teams and builders can apply to assess and harden any AI-assisted IDE deployment.