测试并保障您的LLM应用安全
由30,000+开发者使用的开源LLM测试工具
生成式AI的自动化红队测试
运行定制扫描,检测安全、法律和品牌风险:
npx promptfoo@latest redteam init
我们的探测器会动态适应您的应用,并揭示常见的失败问题,如:
- PII泄露
- 不安全的工具使用
- 跨会话数据泄露
- 直接和间接的提示注入
- 越狱
- 有害内容
- 专业的医学和法律建议
- 以及 更多内容
开发者信赖的公司
Comprehensive security coverage
Custom probes for your application that identify failures you actually care about, not just generic jailbreaks and prompt injections.
Learn MoreBuilt for developers
Move quickly with a command-line interface, live reloads, and caching. No SDKs, cloud dependencies, or logins.
Get StartedBattle-tested, 100% open-source
Used by teams serving millions of users and supported by an active open-source community.
View on GitHubEasy abstractions for complex LLM testing
Simple declarative config
# Test cases are generated to specifically target the system's use case
purpose: 'Budget travel agent'
# Define where payloads are sent
targets:
- id: 'https://example.com/generate'
config:
method: 'POST'
headers:
'Content-Type': 'application/json'
body:
userInput: '{{prompt}}'
Detailed, actionable results