{"id":"prompt-injection-firewall","slug":"prompt-injection-firewall","name":"Prompt-injection / jailbreak firewall","shortName":"Prompt-injection / jailbreak firewall","problemStatement":"Screen untrusted user and retrieved content for instruction-override before it reaches the model — a dedicated firewall, not a content taxonomy.","whenNotTopPick":"Need programmable multi-step rails / topical policies — NeMo Guardrails; only need free hate/sexual/violence flags — OpenAI Moderation; already standardized on Palo Alto — Prisma AIRS; Cisco estate — cisco-ai-defense.","categoryIds":["cat-observability","cat-inference-apis"],"depotPickProviderId":"lakera","depotPickRationale":"capability on injection/jailbreak detection + dx of a single API. Distinct from content-moderation (taxonomy) and llm-input-guardrails (programmable policy engine).","runnersUpIds":["nvidia-nemo-guardrails","openai-moderation","prisma-airs","guardrails-ai","hiddenlayer"],"weights":{"capabilityFit":0.25,"pricePerformance":0.18,"latencyReliability":0.15,"developerDx":0.15,"privacyPosture":0.1,"lockInRisk":0.07,"maturity":0.1},"methodologyNotes":"capability on injection/jailbreak detection + dx of a single API. Distinct from content-moderation (taxonomy) and llm-input-guardrails (programmable policy engine).","tags":["prompt"],"depth":{"whenNotToUse":{"text":"Need programmable multi-step rails / topical policies — NeMo Guardrails; only need free hate/sexual/violence flags — OpenAI Moderation; already standardized on Palo Alto — Prisma AIRS; Cisco estate — cisco-ai-defense.","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"nvidia-nemo-guardrails","name":"NVIDIA NeMo Guardrails","overallForJob":7.87,"pickOverallForJob":8.21,"beatsPickOn":["lockInRisk"],"source":"first resolvable entry of the job's editorially ranked `runnersUpIds`; scores are stored job-weighted scores"},"runnerUpReason":null,"lockIn":{"pickLockInRisk":5.5,"runnerUpLockInRisk":4.5,"scale":"0–10 stored curated estimate; higher = more lock-in (worse)","pickExitSignals":[],"runnerUpExitSignals":["open source (provider tag `oss`)"],"pickNotes":[],"selfHostFallback":[{"id":"llm-guard","name":"LLM Guard","license":"MIT","sourceUrl":"https://raw.githubusercontent.com/protectai/llm-guard/main/LICENSE"}],"migration":"Runner-up NVIDIA NeMo Guardrails has lower stored lock-in risk (4.5 vs 5.5, 0–10, higher = more lock-in). Self-host fallback listed for this job: LLM Guard.","migrationReason":null,"derivedFrom":"stored lockInRisk scores, provider tags (oss, self-host, openai-compat, open-models), free rows that list this job, and verbatim provider notes. No migration guide was invented."}},"freshness":{"pick":{"score":{"asOf":"2026-09-14","ageDays":43,"stale":true,"staleAfterDays":30,"reason":null},"lastReviewed":{"asOf":"2026-09-14","ageDays":43,"stale":true,"staleAfterDays":30,"reason":null},"sourceCheck":{"checkedAt":"2026-10-27","sourceUrls":3,"sourcesReachable":3,"pricingRows":0,"pricingRowsReconfirmed":0,"note":"A source re-check confirms the page is reachable and, for pricing rows, that the stored amount and SKU name appear on it. It does not re-derive or change the score.","reason":null}}}}