Back to browse768489
Promptfoo
ToolOpen-source LLM prompt testing and evaluation
Promptfoo112.0K installs4.5 (1.2K)
82
TrustedSecurity
78
Quality
82
Maintenance
88
Safety Tier Low Risk
Security ScanWarnings
PriceFree
Last Scanned5/11/2026
About
Open-source tool for testing and evaluating LLM prompts against assertions. Runs prompt variations against multiple models, measures quality metrics, and catches regressions before production. Supports red-teaming and security testing.
Tags
Categories
AnalyticsObservability
Security Scan
78/100
11 checks · 9 passed · 2 findings5/13/2026
Scanners:customsemgrepgitleakstrivy
SSRF Detection1
Prompt Injection
Data Exfiltration
Dangerous Commands
Secret Detection1
Obfuscation
External Fetches
Credential Access
Privilege Escalation
Secret Detection (Gitleaks)
Static Security Analysis
Findings (2)
highPrivate IP range accesscustom
Dockerfile:65
criticalPrivate keycustom
src/microsoftSharepoint.ts:102
50 files scanned from repository
Related Tools
Browser Use
Let AI agents control web browsers
ToolFreeScanned
145.6K4.3(892)Browser Use
PythonAny LLM
Composio
250+ app integrations for AI agents
Tool
112.3K4.4(678)Composio
PythonJavaScriptCrewAILangGraph+1
E2B Code Interpreter
Sandboxed code execution for AI agents
ToolScanned
89.7K4.6(534)E2B
PythonJavaScriptAny LLM