THE CYBER TOOLCHAIN
Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.
Strix v1.5.0 lets agents scan OpenAPIOpenAPIA vendor-neutral specification for describing REST APIs in a machine-readable format, maintained by the OpenAPI Initiative. Cyber tools use it to auto-generate clients, documentation, and validation from a single source of truth./Swagger specs and Postman collections directly as targets, rewrites the interactive terminal UI in Go/Bubble Tea, and enriches SCASCASoftware composition analysis, identifying third-party dependencies and checking them for known vulnerabilities and license issues. It covers software a team uses rather than writes itself. findings with dependency-chain and reachability evidence, alongside new LLMLLMA large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. configuration environment variables and performance/security hardening.
what's the number?
Each feature carries 0–100 for how completely the vendor documented it — not how big or important the work is. A major capability described in eight words scores low, and that is the finding.
- depth0–40 what it does and how it works or what changed
- specificity0–30 names real surfaces — APIs, flags, formats, limits, numbers
- actionability0–30 enough to go use it — a named endpoint, flag, or config key tops this; a UI path is a starting point
Code and config rank first by construction: a documented endpoint, flag or config key scores at the top of specificity and actionability, so it sorts above a feature described only in prose. Under 60 the notes go thin — everything below the “thinner coverage” line is thinner documentation, not smaller work. Hover any meter for that feature's three sub-scores.
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.
$ export LLM_EXTRA_HEADERS='{"X-Gateway-Token": "my-gateway-secret"}' export STRIX_LLM="openai/gpt-4o" export LLM_API_KEY="your-api-key" strix --target https://your-app.com
Supports API specs (OpenAPI/Swagger) and Postman collections as scan targets, letting agents test every declared endpoint without crawling.
$ strix --target ./openapi.yaml
Adds STRIX_REASONING_EFFORT=max config option for providers that expose a reasoning-effort control, letting agents push maximum reasoning effort on complex targets.
$ export STRIX_REASONING_EFFORT=max strix --target https://your-app.com
SCA findings now record the full transitive dependency chain, showing how a vulnerable package is pulled in, and 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.
Adds installable SKILL.md skills and AGENTS.md support for extending agent capabilities.
Adds LLM_DISABLE_STREAMING environment variable as an opt-in flag to disable streaming for OpenAI-compatible endpoints that don't support it.
Replaces the Python/Textual TUITUIA text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. with a Go/Bubble Tea interface for the interactive terminal UI.
Delivers ~10x faster CLI startup via lazy imports.
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.