A first task to try
Compare two prompt versions against a small, labeled test set.
Limitations to check
Inspect failures and coverage; a passing evaluation is not a safety certification.
New to the power shelfSecurity tools
Documentation reviewed · 2026-10-07
Not connection-tested or security-audited.
Promptfoo · Security tools
Promptfoo
Evaluate prompts and agents, compare outputs and run configured security tests.
- Hosting
- Local / CI
- Setup style
- Technical setup
- Cost
- Check current provider pricing, app subscriptions and usage charges.
- Compatibility
- Confirm your client, version and plan in the publisher’s setup instructions.
- Permissions
- Tests can call paid model endpoints and process datasets. Use authorized targets and appropriate sample data.
A thoughtful first stepStart with a small task and permitted test data. Review the requested access, and require approval before actions that change external data.
Pricing & publisher resources
Pricing not verified · Check provider
Check current terms with the publisher before purchasing.
Own this tool? Claim or update it ↗Keep this listing useful.
Sign in to keep a private watchlist. Email updates require a separate opt-in in your account.
Report outdated pricing, a broken link or a discontinued tool
Reports are private to you and the review team. A report does not automatically change or remove a listing.
Task fit & availability
Availability not independently verified
A directory listing is not a live uptime guarantee. Check the official publisher before relying on the tool.
Questions for this tool
Loading reviewed questions…
Ask a question about Promptfoo
Sign in with your email in another tab to ask or vote without losing this draft. Your email stays private. Do not include confidential information; approved questions are public.
KNOW YOUR SUPERPOWER
From discovery to your first useful result.
Editorial guidance for evaluating this kind of tool. Suggested tasks have not been independently tested.
01 · WHAT IT IS
A tool that helps inspect a particular class of issue. Its scope and findings need to be understood before acting on them.
02 · WHAT YOU NEED
Identify what the tool checks, what files or systems it reads and how to interpret its output.
03 · A FIRST TASK TO TRY
Compare two prompt versions against a small, labeled test set.
04 · YOUR REVIEW CHECKPOINT
Inspect failures and coverage; a passing evaluation is not a safety certification.
EXPLORE YOUR OPTIONS
Related tools to investigate.
Matched by category or role. These suggestions are not tested equivalents.
MAKE IT USEFUL
Give it a routine.
THE DEVELOPMENT SUPERPOWER
A smaller, cleaner pull request.
Move from issue to reviewed change.
GHC7GlExplore the routine ↗
THE DEVELOPMENT SUPERPOWERGive your bug some context.
Investigate an error without guessing at the cause.
SGHC7Explore the routine ↗
THE DEVELOPMENT SUPERPOWERAn agent with good boundaries.
Pilot one bounded task before adding autonomy.
LgCrGlExplore the routine ↗