$ loading_
Scan prompts and tool inputs to block prompt injection risks.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "io.github.CSOAI-ORG/agent-prompt-injection-firewall-mcp" MCP server from askskill: Run: claude mcp add 'io-github-csoai-org-agent-prompt-injection-firewall-mcp' -- npx -y agent-prompt-injection-firewall-mcp
Detect prompt injections and jailbreaks to secure LLM applications and workflows.
Scan text and URLs for prompt injection risks in AI agents.
Scan inbound and outbound emails for prompt injection, phishing, and secret leaks.
Validate webhook signatures, log events, and replay them for AI agents.
Secure AI agents locally with cost controls, injection blocking, and action approvals.
Scan AI agents for tool-calling vulnerabilities and surface key security risks.