agent-prompt-injection-firewall-mcp is an open-source CLI firewall that scans prompts, RAG documents, tool arguments, and agent-to-agent payloads for OWASP LLM01 prompt injection vulnerabilities. It uses pattern-based and heuristic detection, integrates with MCP, and provides signed attestations for compliance. Designed for AI developers and security teams.
Latest indexed changes and source events
Other apps tracked under the same category.
