https://cybertoolchain.io/tools/lakera New releases and features in Lakera, tracked by The Cyber Toolchain. en Sat, 31 Oct 2026 07:46:07 GMT https://docs.lakera.ai/changelog https://docs.lakera.ai/changelog Sat, 31 Oct 2026 07:46:07 GMT Lakera adds a request latency percentiles chart to the Analytics page showing p25, p50, p75, and p95 over time⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Lakera's Analytics page now shows a request latency percentiles chart plotting the 25th, 50th (median), 75th, and 95th percentile latency of Guard API requests over time, with hover-to-inspect per time bucket and click-to-toggle per percentile.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ Full history on Cyber Toolchain: https://cybertoolchain.io/tools/lakera https://docs.lakera.ai/changelog https://docs.lakera.ai/changelog Mon, 26 Oct 2026 13:39:52 GMT Lakera Analytics page gains a request latency percentiles chart showing p25, p50, p75, and p95 Guard API latency over time.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Adds a request latency percentiles chart to the Analytics page, plotting p25, p50 (median), p75, and p95 latency of Guard API requests over time, with hover-to-inspect and per-percentile show/hide controls.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ Full history on Cyber Toolchain: https://cybertoolchain.io/tools/lakera https://docs.lakera.ai/openapi/guard-api.json https://docs.lakera.ai/openapi/guard-api.json Fri, 18 Sep 2026 07:40:19 GMT API surface changed: 4 modified⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ Breaking changes: • POST /v2/guard: param Authorization (header) removed • POST /v2/guard/results: param Authorization (header) removed • POST /v2/policies/health: param Authorization (header) removed • POST /v2/policies/lint: param Authorization (header) removed Full history on Cyber Toolchain: https://cybertoolchain.io/tools/lakera https://docs.lakera.ai/changelog https://docs.lakera.ai/changelog Mon, 07 Sep 2026 07:33:06 GMT Lakera adds AI Agent Security early access, Policy Impact Simulator, audio debugging flag, and self-hosted request logging. • Adds `audio_payload` flag in Guard audio requests to expose debugging information about the audio sample. • Adds `POLICY_RELOAD_INTERVAL_SECONDS` environment variable to control the configurable policy reload period for self-hosted containers. • Adds `MAX_WARMUP_TOKENS` environment variable (default 50000) to cap warmup tokens in self-hosted containers, using the minimum of `MAX_WARMUP_TOKENS` and `MAX_INPUT_TOKENS`. • Adds `/metrics` endpoint to expose telemetry data for self-hosted deployments. • Adds Request Logging for self-hosted deployments suitable for monitoring solutions such as Elastic Stack. • New AI Agent Security (Early Access) product extends AI Guardrails with discovery and risk assessment for agents your organization builds and deploys. • New Policy Impact Simulator in the Dashboard shows how different sensitivity levels and guardrail configurations would have affected historical traffic. • Guard API breakdown response now includes a `result` field for each detector showing confidence level (`l1_confident`, `l2_very_likely`, `l3_likely`, `l4_less_likely`, `l5_unlikely`). • Adds support for `developer` and `tool` roles for messages in the API to cover agentic and tool-using use cases. • Expands API coverage to include `tool` role and `tool_calls` to better support agentic workflows. • Adds GPU support for self-hosted containers, compatible with any CUDA 12.x GPU, accelerating request processing. • Adds support for Portuguese language in Prompt Defense. • Adds HTTPS endpoint support for Guard. • Adds user-defined prompt Allow/Deny lists to customise detection behaviour, with Allow/Deny list detections shown in the Request Details page. • Adds weapons detector (firearms, bombs, missiles, bladed weapons, other personal weapons) and crime detector as new Content Moderation detectors. • Gateway now logs requests to `v2/guard/audio` for monitoring purposes. • Enhanced guardrails overview table with filtering functionality and a 'Policies' column; guardrails page adds 'creator' field and 'last edited by/at' information. • Enhanced SaaS Requests page adds filtering and ordering of columns, `request_id` field, and shareable URL-based filter views. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/lakera https://docs.lakera.ai/openapi/guard-api.json https://docs.lakera.ai/openapi/guard-api.json Fri, 14 Aug 2026 09:52:09 GMT API surface changed: 1 modified • POST /v2/guard: response schema changed Full history on Cyber Toolchain: https://cybertoolchain.io/tools/lakera https://docs.lakera.ai/changelog https://docs.lakera.ai/changelog Wed, 15 Jul 2026 01:22:57 GMT Lakera adds AI Agent Security (Early Access), Policy Impact Simulator, per-detector confidence levels, and a self-harm subcategory to content moderation. • New `result` field in Guard API breakdown responses exposes per-detector confidence levels (`l1_confident` through `l5_unlikely`), matching the granularity already available in `/guard/results`. • New `self-harm` sub-category added to the content moderator detector. • New product: AI Agent Security (Early Access) — discovers and inventories agents, their tools, and connected MCP servers across Amazon Bedrock, Amazon Bedrock AgentCore, Google Cloud, Microsoft Copilot Studio, Salesforce Agentforce, n8n, and Relevance AI. • AI Agent Security provides per-agent risk ratings (Critical / High / Medium / Low) with contributing factors, plus a risk-types view mapped to OWASP and MITRE ATLAS. • New Policy Impact Simulator on the dashboard shows how different sensitivity levels and guardrail configurations would have affected historical traffic, with flagging-rate comparisons across L1–L4 and category-level breakdowns. • Audio requests now expose an `audio_payload` flag in the Guard API request for access to debugging information of the audio sample. • Gateway now logs requests to `v2/guard/audio` for monitoring purposes. • TensorRT-LLM audio processing gains denoising support. • Added support for `developer` and `tool` roles in API messages to cover agentic and tool-using use cases. • Guardrails overview table gains filtering functionality and a new 'Policies' column; guardrail detail pages now show 'creator', 'last edited by/at', and 'Policies assigned' fields. • Logs page adds a 'Link' button for shareable navigation with or without current filters. • Misclassification submissions now support bulk operations across multiple logs. • Policy advanced settings redesigned with dedicated sections for Content Moderation, Data Leakage Prevention, Prompt Defense, and Unknown Links. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/lakera