Snyk DeepCode AI helps review code and identify security issues, with autofix features for developers.
promptfoo
Promptfoo helps developers build and test AI applications by identifying security vulnerabilities during development.
About promptfoo
Promptfoo helps developers build and test AI applications by identifying security vulnerabilities during development. It provides automated red teaming for agents and RAG systems, generating context-aware tests for prompt injections, jailbreaks, data and PII leaks, business rule violations, and insecure tool use.
It connects to AI apps, agents, and workflows, including CI/CD pipelines, GitHub, GitLab, Jenkins, and MCP and agent frameworks, with on-premise or cloud use. It shows security findings in pull requests with remediation steps and supports continuous monitoring.
Key features
- Automated red teaming for agents and RAG systems
- Tests direct and indirect prompt injections
- Tests jailbreaks, data and PII leaks
- Checks business rule violations and insecure tool use
- Integrates with CI/CD pipelines and GitHub, GitLab, Jenkins
- Provides remediation guidance in pull requests
Best for: Developers and security teams building AI agents and RAG applications that need vulnerability testing during development.
Good for
- Connects to CI/CD pipelines and existing developer workflows
- Tests application-specific logic including RAG, agents, and integrations
- Provides remediation guidance directly in pull requests
promptfoo at a glance
- Website
- promptfoo.dev
- Type
- Website
- Pricing
- Not confirmed. Check the site
- Platforms
- Web
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
promptfoo alternatives
Tools and sites you could use instead, ranked by how closely they match.
Sourcery reviews pull requests in GitHub and GitLab, identifying bugs and suggesting summaries and one-click fixes.
Qodo reviews code with codebase context and supports workflows for IDEs, pull requests, and security.
Prediction Guard provides a self-hosted platform for applying NIST and OWASP policies to models and agents.
Greywall provides a deny-by-default sandbox for AI coding agents, with kernel-enforced isolation on Linux and macOS.
Open source
15 alternatives
rehydra scans LLM prompts for accidental personal information before they reach a model.
Open source
17 alternativesPopular in AI Code Review & Testing
Well-known listings from the same topic.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.