prompt_injection_firewall_v3_1

Current plans

Direct accepted alternatives

Vaultak · job 73%Shrike Security · job 84%guard_mail · job 71%Evo · job 81%promptscan · job 78%Shield · job 76%Endpoint Protector · job 84%nullcone · job 78%AIM Guard · job 79%Agent Guardrail · job 72%Akto AI Agent Security Platform · job 77%ClawGuard Shield · job 72%agent_security_scanner · job 74%CCS Runtime Evidence MCP Server · job 74%heeler · job 78%mcp-skill-sec · job 73%MCP Security Scanner Server · job 74%sentinel_2 · job 72%Percentages are graph-similarity metadata, not suitability scores. A graph edge answers “is it connected” — plan fit and comparable cost are checked below.

Inspect histories

Pick the exact reference and alternative series. Each history is separate; gaps stay gaps.

This view calls the same get_evidence tool your agent would — chart, table and MCP response describe the same records. Watch the reference series