promptfoo
Promptfoo (OpenAI) · Open Source · Trust 97Automatically tests prompts, agents and RAG apps and runs red-teaming and vulnerability scans locally. Now part of OpenAI, still open source.
Make it safe · Alternatives
Alternatives to Mindgard
Mindgard by Mindgard belongs to the area “Make it safe” on OROBO. Here are 8 alternatives from the same area, first 8 with the same goals. Every entry is checked automatically every day (origin, code patterns, licence, maintenance, reachability); OROBO does not check whether software fits your purpose.
8 alternatives at a glance
Snyk Agent Scan (formerly Invariant MCP-Scan)
Snyk (ex-Invariant Labs team) · Open Source · Trust 100Scans installed MCP servers and agent skills for tool poisoning, hidden instructions and malware; includes a web inspector.
Cisco Skill Scanner
Cisco AI Defense · Open Source · Trust 100Inspects agent skills for prompt injection, data exfiltration and malicious code patterns before installation.
Docker MCP Gateway
Docker · Open Source · Trust 100Runs MCP servers isolated in containers, manages secrets safely and allows only approved tools.
Cisco MCP Scanner
Cisco AI Defense · Open Source · Trust 100Checks MCP servers and their tools with YARA rules, LLM analysis and package checks for hidden attacks.
Cisco AI Defense
Cisco · Paid · limited checksDiscovers AI use in a company, red-teams models and enforces guardrails for agents at the network level.
F5 AI Guardrails & AI Red Team (formerly CalypsoAI)
F5 (CalypsoAI) · Paid · limited checksModel-agnostic runtime protection for AI models and agents, paired with automated attack simulations.
HiddenLayer AISec Platform
HiddenLayer · Paid · limited checksPlatform with a model scanner, automated red teaming and runtime protection for AI agents and coding agents.
Keep comparing
All software in “Make it safe” with filters by price, offline use and difficulty.