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 Snyk Agent Scan (formerly Invariant MCP-Scan)
Snyk Agent Scan (formerly Invariant MCP-Scan) by Snyk (ex-Invariant Labs team) 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
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.
Akto
Akto · Open Source · Trust 97Discovers MCP servers and AI agents in a company and automatically tests them and their APIs for flaws.
garak
NVIDIA · Open Source · Trust 100Command-line scanner that probes a language model with hundreds of attacks for jailbreaks, leaks and hallucinations.
Guardrails AI
Guardrails AI (Harvey) · Open Source · Trust 100Python framework with validators that check AI inputs and outputs and enforce structured responses. Part of Harvey since September 2026.
NeMo Guardrails
NVIDIA · Open Source · Trust 100Toolkit for programmable guardrails: keeps chatbots on topic, masks personal data and blocks jailbreaks.
Keep comparing
All software in “Make it safe” with filters by price, offline use and difficulty.