Why does my AI write code that is correct in isolation but insecure in my system?
機会
AI coding assistants generate code that is syntactically valid and functionally correct at the function level but have no model of the security invariants of the surrounding system: the trust boundaries, IAM policies, data classification, and threat model that make a pattern safe or dangerous in a specific codebase. The result is structurally valid code that exposes tokens in logs, omits row-level access checks, or misconfigures permissions in ways an engineer familiar with the system would catch immediately. CVE-2025-48757 is a concrete case where an AI tool generated database schemas without row-level security, silently exposing 170 production applications. Research shows AI-assisted commits leak secrets at more than twice the rate of human-only commits. No current assistant ingests or reasons about a codebase's existing security model before generating code.
重要な理由
Security context unawareness produces a class of vulnerabilities that pass every syntax check and unit test but are trivially exploitable once deployed.
機会をどう評価するか
Opportunity Scoreは測定値ではなく、私自身の見解です。どれほど痛みを伴うか、どれほど頻繁に影響を与えるか、そして今日時点で解決策がいかに少ないか。スコアが高いほど、構築する価値が高いと私は考えています。
それが現れたときにどれほどの痛みをもたらすか。
実際にどれほど頻繁に人々がそれに直面するか。
今日時点で、それに対する優れたツールがいかに少ないか。