https://cybertoolchain.io/tools/strix New releases and features in Strix, tracked by The Cyber Toolchain. en Mon, 05 Oct 2026 02:39:14 GMT https://github.com/usestrix/strix/releases/tag/v1.7.0 https://github.com/usestrix/strix/releases/tag/v1.7.0 Mon, 05 Oct 2026 02:39:14 GMT Strix v1.7.0 adds `--fail-on` severity gating, `STRIX_API_TYPE` forcing, `budget_policy=pause`, lazy MCP connections, and an interactive `--resume` picker.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Adds `--fail-on` flag to the CLI to gate headless exit code on finding severity, enabling CI pipelines to fail on configurable severity thresholds.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ • Adds `STRIX_API_TYPE` environment variable to force the Responses API vs chat completions endpoint, overriding model-based auto-detection. • Adds `budget_policy=pause` to park every agent at the cost limit until the operator explicitly resumes, preventing runaway spend. • Adds a structured per-attempt provider request log with provider request IDs for LLM call traceability. • Adds lazy initialization of MCP connections so connections are not established until actually needed. • Adds interactive run picker when `--resume` is supplied with no run name, letting operators choose from prior runs in the terminal. • Adds the ability for agents to delete a vulnerability report they previously filed. • Requires `http_exchange_ids` for proxy-validated findings, linking HTTP exchange evidence directly to reported vulnerabilities. • Prompts agents to include local Git blame in technical details of findings. • Makes `read_only` local sources become `:ro` bind mounts in the container runtime. • Animates the `wait_for_agents` indicator in the TUI. • Lets the verified user define and change scope interactively in chat. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/strix https://github.com/usestrix/strix/releases/tag/v1.6.2 https://github.com/usestrix/strix/releases/tag/v1.6.2 Sat, 05 Sep 2026 01:30:11 GMT Strix v1.6.2 adds Exa as a web search provider alongside Perplexity and improves error telemetry with phase and exception-class classification. • Adds Exa as a web search provider alongside Perplexity for agent-driven reconnaissance. • Classifies error beacons by phase and exception class in telemetry for richer operational diagnostics. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/strix https://github.com/usestrix/strix/releases/tag/v1.6.1 https://github.com/usestrix/strix/releases/tag/v1.6.1 Wed, 02 Sep 2026 16:10:57 GMT Strix v1.6.1 adds GLM-5.3, Fable 5.1, and Gemini 3.7 Flash to the recommended model list, with `openrouter/z-ai/glm-5.3` as the new top pick. • Adds `openrouter/z-ai/glm-5.3` as the new top recommended model, with GLM-5.3, Fable 5.1, and Gemini 3.7 Flash added to the recommended model list. • MCP call errors no longer quarantine the connection, keeping MCP integrations live after transient failures. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/strix https://github.com/usestrix/strix/releases/tag/v1.6.0 https://github.com/usestrix/strix/releases/tag/v1.6.0 Tue, 01 Sep 2026 20:33:42 GMT Strix v1.6.0 adds MCP server support, a managed cloud CLI, workspace file injection, OWASP LLM Top 10 2026 skills, and contextual CVSS dependency reports. • Adds `--workspace-file` CLI flag and `extra_files` config key to place caller-provided files into the sandbox workspace before a scan starts. • Adds `strix cloud` subcommand for the managed platform CLI, covering login, scans, billing, and the full cloud API. • Adds `update_vulnerability_report` agent API so an agent can revise an already-filed finding during a run. • Adds `--host` option to `strix view` to expose the local results viewer on a custom interface (e.g. `--host 0.0.0.0`). • Adds MCP server support, with connections isolated per task, on-demand tool resolution instead of bulk registration, and connection status surfaced in the UI; connections survive transient transport failures. • Adds contextual CVSS breakdown and required usage evidence on dependency vulnerability reports. • Adds OWASP LLM Top 10 2026 skill coverage. • Adds Azure and Entra security skill. • Adds argument injection security skill. • Adds ecosystem supply-chain security skills. • Adds Hurl and Hypothesis security playbooks. • Adds semantic browser and Electron security skills. • Promotes coverage as a first-class artifact with evidence discipline in the agent layer. • Hardens CSV injection in report output. • Bootstraps Caido concurrently with scan start, reducing scan startup latency. • Moves heavy imports off the startup path and pre-warms them in the background, reducing CLI startup time. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/strix https://github.com/usestrix/strix/releases/tag/v1.5.1 https://github.com/usestrix/strix/releases/tag/v1.5.1 Fri, 07 Aug 2026 17:32:43 GMT Strix v1.5.1 expands Firebase Storage rules coverage in its vulnerability scanner. • Expands Firebase Storage rules coverage for misconfiguration detection. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/strix https://github.com/usestrix/strix/releases/tag/v1.5.0 https://github.com/usestrix/strix/releases/tag/v1.5.0 Fri, 07 Aug 2026 02:16:36 GMT Strix v1.5.0 adds LLM_EXTRA_HEADERS, LLM_DISABLE_STREAMING, STRIX_REASONING_EFFORT, API spec/Postman targets, a Go/Bubble Tea TUI, and richer SCA reporting. • Adds `LLM_EXTRA_HEADERS` environment variable to inject custom request headers into any OpenAI-compatible endpoint, enabling use with proxies, gateways, or auth-requiring local models. • Adds `LLM_DISABLE_STREAMING` environment variable as an opt-in flag to disable streaming for OpenAI-compatible endpoints that don't support it. • Adds `STRIX_REASONING_EFFORT=max` config option for providers that expose a reasoning-effort control. • Supports API specs (OpenAPI/Swagger) and Postman collections as scan targets, letting agents test every declared endpoint without crawling. • Replaces the Python/Textual TUI with a Go/Bubble Tea interface for the interactive terminal UI. • SCA findings now record the full transitive dependency chain, showing how a vulnerable package is pulled in. • SCA findings now include a structured reachability evidence ladder for dependency vulnerabilities, grading confidence from theoretical to exploitable. • Dependency CVE findings now require a repo-relative `manifest_path` field, giving precise location context in reports. • Mounts local targets into the sandbox instead of copying them, reducing startup overhead for local directory scans. • Credential files are now created with owner-only permissions, hardening local secret storage. • Delivers ~10x faster CLI startup via lazy imports. • Adds installable `SKILL.md` skills and `AGENTS.md` support for extending agent capabilities. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/strix https://github.com/usestrix/strix/releases/tag/v1.4.0 https://github.com/usestrix/strix/releases/tag/v1.4.0 Mon, 27 Jul 2026 11:59:57 GMT Strix v1.4.0 adds self-update, ChatGPT inference, Linux ARM64, Bedrock prompt caching, and smarter context management for long scans. • Adds `strix --update` command for in-place CLI self-update and automatic update notifications. • Supports signing in with a ChatGPT subscription as an inference provider. • Adds Linux ARM64 standalone release builds. • Enables AWS Bedrock/Anthropic prompt caching for Claude models to reduce latency and cost on repeated context. • Adds a dedicated deduplication model to reduce duplicate findings across scan runs. • Adds `list_reports` and `get_report` read-only tools for programmatic report access. • Introduces model-aware conversation compaction to keep long scans within context limits. • Bounds per-tool output before it enters agent history, and spills oversized output to the sandbox workspace instead of dropping it. • Adds graduated wrap-up warnings, a budget reserve, and an interactive budget pause/continue flow during scans. • CLI now exits after a scan completes instead of launching a local viewer — use `strix view` to open results separately. Breaking changes: • Strix now quits after a scan completes instead of hosting a local viewer — workflows that relied on the viewer launching automatically must now run `strix view` separately. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/strix https://github.com/usestrix/strix/releases/tag/v1.3.0 https://github.com/usestrix/strix/releases/tag/v1.3.0 Wed, 22 Jul 2026 16:27:56 GMT Strix v1.3.0 adds a Feedback & support tab and a prominent scan switcher with pentest terminology to the local viewer UI. • Adds a Feedback & support tab to the local viewer UI. • Adds a prominent scan switcher to the local viewer with renamed 'pentest' terminology. • Shrinks the sandbox Docker image from 7.2 GB to 3.8 GB via cache cleanup, multi-stage Go build, and dropping ZAP — enabling use on disk-constrained environments. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/strix https://github.com/usestrix/strix/releases/tag/v1.2.0 https://github.com/usestrix/strix/releases/tag/v1.2.0 Tue, 21 Jul 2026 16:11:47 GMT Strix v1.2.0 adds recon asset-discovery skill, AD/Kerberos testing, Docker resource limits, shared-network port resolution, and a local run viewer with email reports. • Adds a recon asset-discovery skill for automated attack surface enumeration. • Adds an Active Directory / Kerberos domain testing skill for enterprise network assessments. • Adds a Grafana/Prometheus observability pivot skill to identify exposed monitoring infrastructure. • Enables opt-in resource limits (CPU/memory) for Docker sandbox containers to cap agent resource usage. • Introduces a local run viewer with email report delivery, run history, and access to the full platform suite. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/strix https://github.com/usestrix/strix/releases/tag/v1.1.0 https://github.com/usestrix/strix/releases/tag/v1.1.0 Tue, 14 Jul 2026 11:47:01 GMT Strix v1.1.0 adds 9 new security skills, SARIF 2.1.0 output, budget controls, and multi-target list scanning. • Adds weak-password detection and LLM prompt-injection security skills. • Adds GCP and Auth0 reconnaissance skills. • Adds five new security skills covering OAuth, AWS, prototype pollution, deserialization, and Django. • Adds skill-directory registration for extending the skill set. • Emits SARIF 2.1.0 output for GitHub code-scanning and ASPM ingestion. • Tags SARIF rules with STRIDE categories derived from CWE mappings. • Adds `--max-budget-usd` flag to cap token/cost spend per scan. • Adds bind-mount option to handle large target repositories without copying them into the sandbox. • Adds `--target-list` CLI option to supply multiple targets from a file. • Adds new dependency reporting fields and requires `advisory_cvss` for dependency findings, with a new SCA TUI renderer. • Adds `force_required_tool_choice` setting for finer LLM tool-calling control. • Warns when the configured LLM is not a recommended or frontier model. • Routes ollama models through `ollama_chat` provider so tool calling works correctly. • Reports cost for streamed OpenRouter calls and attributes OpenRouter usage to the Strix app. • Adds TUI 'More content available' hint for long views and throttled refresh with render caching to reduce scroll stutter. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/strix https://github.com/usestrix/strix/releases/tag/v1.0.3 https://github.com/usestrix/strix/releases/tag/v1.0.3 Tue, 09 Jun 2026 01:10:24 GMT Strix v1.0.3 adds LiteLLM cost visibility, TUI status updates, and registry-gated reasoning. • `reasoning_effort` is now gated by the LiteLLM model registry; effort parameters are only sent when the underlying model supports them • Use observed LiteLLM cost for LiteLLM-routed calls instead of estimated costs Full history on Cyber Toolchain: https://cybertoolchain.io/tools/strix https://github.com/usestrix/strix/releases/tag/v1.0.0 https://github.com/usestrix/strix/releases/tag/v1.0.0 Tue, 26 May 2026 21:51:38 GMT Strix v1.0.0 adds native tool calling, save/resume, multi-agent control, new skills and providers • Enables save and resume workflow for long-running agent sessions • Adds native tool calling capability for integrated cyber tooling • Supports multi-agent control workflows • Adds Kubernetes security testing skill • Adds NoSQL injection vulnerability skill • Adds SSTI and Header Injection vulnerability skills • Adds Novita AI as a supported LLM provider Full history on Cyber Toolchain: https://cybertoolchain.io/tools/strix https://github.com/usestrix/strix/releases/tag/v0.8.3 https://github.com/usestrix/strix/releases/tag/v0.8.3 Mon, 23 Mar 2026 05:16:53 GMT Strix v0.8.3 adds NestJS skills, interactive agent loop mode, and OpenTelemetry tracing support. • feat(skills): adds a NestJS security testing module for skill-based scanning • `feat`: adds interactive mode for the agent loop to allow manual stepping through prompts Full history on Cyber Toolchain: https://cybertoolchain.io/tools/strix https://github.com/usestrix/strix/releases/tag/v0.8.2 https://github.com/usestrix/strix/releases/tag/v0.8.2 Tue, 24 Feb 2026 02:47:38 GMT Strix v0.8.2 exposes the Caido proxy port for human-in-the-loop workflows. • Exposes the Caido proxy port to enable human-in-the-loop interception during automated scans. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/strix https://github.com/usestrix/strix/releases/tag/v0.8.0 https://github.com/usestrix/strix/releases/tag/v0.8.0 Thu, 19 Feb 2026 22:18:31 GMT Strix v0.8.0 adds mouse text selection auto-copy in TUI and nested XML vulnerability reports • Adds mouse text selection auto-copy to clipboard in the terminal UI (TUI) • Redesigns vulnerability reporting output to include nested XML code locations and CVSS scores Full history on Cyber Toolchain: https://cybertoolchain.io/tools/strix https://github.com/usestrix/strix/releases/tag/v0.7.0 https://github.com/usestrix/strix/releases/tag/v0.7.0 Fri, 23 Jan 2026 19:10:44 GMT Strix v0.7.0 adds --config for .env overrides and migrates skills to Markdown • Accepts `--config` flag to override `.env` variables at runtime • Skills now use Markdown format instead of Jinja templates Full history on Cyber Toolchain: https://cybertoolchain.io/tools/strix https://github.com/usestrix/strix/releases/tag/v0.6.0 https://github.com/usestrix/strix/releases/tag/v0.6.0 Mon, 12 Jan 2026 17:26:14 GMT Strix v0.6.0 adds STRIX_REASONING_EFFORT env var, LLM deduplication, persistent config to ~/.strix/cli-config.json, and a live TUI panel • `STRIX_REASONING_EFFORT` environment variable controls reasoning depth and latency/quality tradeoffs for agents. • LLM-based vulnerability deduplication detects semantically similar findings and merges them into a single canonical entry. • Centralized configuration persists settings to `~/.strix/cli-config.json` across sessions. Breaking changes: • The `--run-name` CLI argument has been removed. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/strix https://github.com/usestrix/strix/releases/tag/v0.5.0 https://github.com/usestrix/strix/releases/tag/v0.5.0 Mon, 15 Dec 2025 18:34:10 GMT Strix v0.5.0 adds configurable scan modes, a standalone binary installer, and an agent todo tool • `--scan-mode` CLI flag with `quick`, `standard`, and `deep` options for controlling scan depth • Standalone binary installation via the `curl -sSL https://strix.ai/install | bash` one-liner • Agent todo system allowing tasks to be tracked as pending or done Full history on Cyber Toolchain: https://cybertoolchain.io/tools/strix https://github.com/usestrix/strix/releases/tag/v0.4.0 https://github.com/usestrix/strix/releases/tag/v0.4.0 Tue, 25 Nov 2025 16:41:08 GMT Strix v0.4.0 adds `--instruction` file support, real-time result persistence to disk, live stats panel, and IP scanning • Adds `--instruction` flag to accept file-based pentest configs instead of CLI strings • Enables real-time results persistence: findings are written to disk as they are discovered • Adds a live agent stats panel (vulnerabilities, tokens, cost, active agents) in both TUI and CLI • Adds IP address scanning support for targets not fronted by hostnames • Adds prompt modules for Open Redirect, Subdomain Takeover, and Info Disclosure Full history on Cyber Toolchain: https://cybertoolchain.io/tools/strix https://github.com/usestrix/strix/releases/tag/v0.3.1 https://github.com/usestrix/strix/releases/tag/v0.3.1 Sat, 01 Nov 2025 12:08:14 GMT Strix v0.3.1 adds headless CLI mode via `--non-interactive`, multi-target scanning, and per-severity findings summary. • Adds `--non-interactive` flag to run Strix in headless mode for automation and CI/CD integration • Enables multi-target scanning to assess repos, URLs, and APIs in a single execution • Includes color-coded per-severity vulnerability counts in the completion panel • Increases default agent `max_iterations` limit from prior version to 300 Full history on Cyber Toolchain: https://cybertoolchain.io/tools/strix