TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Detecting sensitive data shared with OpenAI

7 点作者 gmontard大约 2 年前
Hi HN,<p>I&#x27;m Guillaume, the founder of Bearer, an Open Source code security scanning tool. Despite the buzz around generative AI (which, as a reader of HN, you&#x27;ve likely encountered), we&#x27;ve also heard concerns from security teams.<p>When using OpenAI’s developer APIs (and other LLMs), considering how Generative AI model works, essentially the more you give, the better you receive, we essentially open the door to “overshare” information. For example, If you are building an AI assistant into your travel booking app, sending sensitive data as customer information becomes highly probable. Though, as with any shared data, this does present important security and privacy risks that we can’t overlook, hence the fear of security teams.<p>To address these risks, we must have explicit policies and a culture of privacy and security within the organization. We should treat generative AI models like any other third-party dependency, assessing them for vulnerabilities and safeguarding customer data. Of course, having appropriate tooling also helps.<p>That&#x27;s why we&#x27;ve added a new set of rules to Bearer CLI, our open-source static analyzer, that explicitly checks for OpenAI usage. Combined with our sensitive data detection capability, this feature can alert you and your team if your code is sending sensitive data it shouldn&#x27;t be.<p>You can find a link to Bearer CLI and the specific OpenAI ruleset in the following URLs:<p>Bearer CLI: https:&#x2F;&#x2F;github.com&#x2F;bearer&#x2F;bearer OpenAI&#x27;s rule for JavaScript: https:&#x2F;&#x2F;docs.bearer.com&#x2F;reference&#x2F;rules&#x2F;javascript_third_parties_openai&#x2F;<p>Please feel free to test it with your code and share any feedback with us below. We welcome contributions to improve detection and add new rules to further enhance the security of your code.

1 comment

cfabianski大约 2 年前
I&#x27;m Cédric, CTO @ Bearer<p>I hope you will find this useful but I really enjoyed writing this one to help protect us (users) better. Let me know if there is anything you would like to improve.<p>Link to the Rule <a href="https:&#x2F;&#x2F;github.com&#x2F;bearer&#x2F;bearer-rules&#x2F;blob&#x2F;main&#x2F;javascript&#x2F;third_parties&#x2F;openai.yml">https:&#x2F;&#x2F;github.com&#x2F;bearer&#x2F;bearer-rules&#x2F;blob&#x2F;main&#x2F;javascript&#x2F;...</a> Link to the Recipe <a href="https:&#x2F;&#x2F;github.com&#x2F;Bearer&#x2F;bearer&#x2F;blob&#x2F;main&#x2F;pkg&#x2F;classification&#x2F;db&#x2F;recipes&#x2F;openai.json">https:&#x2F;&#x2F;github.com&#x2F;Bearer&#x2F;bearer&#x2F;blob&#x2F;main&#x2F;pkg&#x2F;classificatio...</a>