https://cybertoolchain.io/tools/arcjet New releases and features in Arcjet, tracked by The Cyber Toolchain. en Wed, 14 Oct 2026 00:00:00 GMT https://arcjet.com/blog/how-we-built-ai-agent-behavior-drift-analysis-with-cloudflare-clef https://arcjet.com/blog/how-we-built-ai-agent-behavior-drift-analysis-with-cloudflare-clef Wed, 14 Oct 2026 00:00:00 GMT Arcjet adds AI agent behavior drift analysis with cross-session state tracking, Cloudflare Clef scoring, and Rego-based Guard policy enforcement.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Adds cross-session risk analysis for coding agents (Claude Code, Codex, Cursor, Muse Code, GitHub Copilot, and custom agents) that flags a session as tainted when it detects prompt injection in tool results, PII in files the agent read, or action sequences resembling credential theft.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Uses `@cf/cloudflare/clef-flash` via env.AI.run() to score structured, typed questions (yes/no probability, multiple-choice distribution, scale position) over session activity sequences — replacing broad single-question hazard checks. • Stores per-session risk state in a Cloudflare Durable Object (created on demand per session) that serializes writes, exposes active flags and explanations, and is readable by the next hook request with minimal latency. • Separates sequence review questions into four categories: factual hazard, evidence sufficiency, triage (drives highlight notifications), and containment (drives session locking) — with different score thresholds for highlights versus locks. • Enforces session taint via a Rego Guard policy that reads `session_flags` from the session Durable Object on every tool call, with risky tool categories (`shell`, `web`, `mcp`, `file_write`) and lock-trigger flag names (`prompt_injection`, `data_exfiltration`, `code_execution_risk`, `sensitive_data_exposure`, `elevated_risk`, `credential_acce…`) defined as named sets. • Applies a scorer isolation rule preventing Arcjet's own output (narratives, model verdicts, taint rows, lock-caused denials) from feeding back into the Clef scoring state, so analysis is grounded only in raw agent actions. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/arcjet https://blog.arcjet.com/sdk-releases-security-briefing-improvements-new-activity-view/ https://blog.arcjet.com/sdk-releases-security-briefing-improvements-new-activity-view/ Fri, 03 Jul 2026 12:00:03 GMT Arcjet adds proxy support, Nosecone Nonce API, enhanced security briefings, and a new Console activity view. • Adds proxy support to the JS SDK 1.6. • Introduces an optimized Wasm bundle across JS, Go, and Python SDKs. • Delivers the first numbered Go SDK release (0.1.0) with improved per-request caching. • Adds a `nonce` function to the Nosecone Next.js library (v1.6.1), enabling nonce access from Server Components and Route Handlers. • Expands weekly security briefing emails with detailed threat tagging, country breakdowns, and updated recommendations. • Opens a new activity view in the Arcjet Console, surfacing non-HTTP Guard events (e.g., agentic file-access events) alongside web requests. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/arcjet https://arcjet.com/blog/sdk-performance-releases-and-proxy-detection https://arcjet.com/blog/sdk-performance-releases-and-proxy-detection Fri, 12 Jun 2026 00:00:00 GMT Arcjet JS SDK adds trusted proxy configuration for Cloudflare and updates Wasm bot detection performance. • Rebuilds the secure Wasm bot detection component with per-request performance optimizations and reduced bundle size Full history on Cyber Toolchain: https://cybertoolchain.io/tools/arcjet https://arcjet.com/blog/announcing-advanced-bot-signals-to-detect-automation-without-captchas https://arcjet.com/blog/announcing-advanced-bot-signals-to-detect-automation-without-captchas Wed, 03 Jun 2026 00:00:00 GMT Arcjet introduces Advanced Bot Signals to detect browser automation without CAPTCHAs using client-side telemetry. • Adds a new client-side signal collection mechanism that loads a WebAssembly module in the browser and stores results in the `aj_signals` cookie for server-side validation • Adds a named bot rejection reason `ARCJET_SIGNALS` returned by the bot detection rule when advanced signals indicate automation Full history on Cyber Toolchain: https://cybertoolchain.io/tools/arcjet https://arcjet.com/blog/designing-a-cli-for-ai-agents https://arcjet.com/blog/designing-a-cli-for-ai-agents Tue, 02 Jun 2026 00:00:00 GMT Arcjet announces design principles for its agent-safe CLI, introducing structured error codes, confirmation envelopes, and token-based auth. • Implements distinct exit codes (0-4) with JSON error bodies on stderr to enable programmatic branching by AI agents • Introduces a mutation confirmation protocol using `--confirm` flag that returns a JSON envelope in stdout before execution • Adds automatic detection of non-TTY stdout to default to structured JSON output for agent workflows • Supports the `ARCJET_TOKEN` environment variable as the primary authentication mechanism, bypassing browser flows for CI/agent environments • Enables field filtering via `--fields` flag to limit JSON output top-level keys and reduce context window usage Full history on Cyber Toolchain: https://cybertoolchain.io/tools/arcjet https://arcjet.com/blog/unified-skills-python-docs-email-management https://arcjet.com/blog/unified-skills-python-docs-email-management Fri, 22 May 2026 00:00:00 GMT Arcjet unifies coding agent skills into a single `arcjet/skills` package with expanded Python docs and email notification management. • Adds email notification management allowing individual subscription control for weekly briefings, quota usage, and trial progress • Expands Python SDK documentation with examples for FastAPI and Flask Full history on Cyber Toolchain: https://cybertoolchain.io/tools/arcjet https://arcjet.com/blog/serving-ai-models-with-open-inference-protocol-apis https://arcjet.com/blog/serving-ai-models-with-open-inference-protocol-apis Wed, 20 May 2026 00:00:00 GMT Arcjet introduces prompt injection detection using hosted LLMs via Open Inference Protocol v2 • Adds a new `prompt-injection-detect` model-backed building block for identifying jailbreak attempts and adversarial inputs. • Implements the Open Inference Protocol v2 (KServe v2) as the standard API contract between Python model services and the Go decision service. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/arcjet