Test LLM outputs
Actively maintainedpromptfoo/promptfoo-action · MIT
The GitHub Action for Promptfoo. Test your prompts, agents, and RAGs. AI Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration.
★ 72 starsLast commit 20 days agoLatest v1.3
B
74
/ 100
Security signals
OpenSSF ScorecardNo data
SECURITY.md presentYes
Immutable releasesNot enabled
Known vulnerabilitiesNone on record
How to use it safely
Recommended: pin to commit SHA
uses: promptfoo/promptfoo-action@04839e664f52212b877170219dab0d7ad2bf6440 # v1.3Mutable tags like v1.3 can be rewritten to point at malicious commits. Pinning to the full commit SHA is the only reference GitHub guarantees immutable.
Full workflow example
steps: - uses: promptfoo/promptfoo-action@04839e664f52212b877170219dab0d7ad2bf6440 # v1.3
Score breakdown
Security (35%)75
Popularity (20%)40
Maintenance (30%)100
Reliability (15%)64
Add this badge to your README
Markdown
[](https://actionrank.dev/actions/promptfoo-promptfoo-action)HTML version
HTML
<a href="https://actionrank.dev/actions/promptfoo-promptfoo-action"><img src="https://actionrank.dev/api/badge/promptfoo-promptfoo-action" alt="ActionRank score"></a>Free to use, no attribution required — the badge updates itself as the score changes. How badges work