CoreLayer AI Security Platform logoCoreLayer AI Security Platform
DashboardQuickstart

CoreLayer AI Security Platform

Secure AI from configuration to runtime. CoreLayer checks AI systems before release, during testing, at deployment, and in production. Run the CLI locally or in CI. Use the dashboard to track the results.

Start hereQuickstartInstall, log in, and run your first scan in about five minutes.TerminalCLI referenceEvery command, flag, and exit code across the four phases.BrowserCoreLayer Security ConsoleFindings, models, users, and reports, organised by role.AccessAuthenticationBrowser-based login, credential storage, and CI tokens.

Install the CLI

One command on macOS or Linux. The CLI is a single static binary. You do not need an account to download it, only to send results to a dashboard.

Terminal
curl -fsSL https://get.corelayersecurity.com/install.sh | sh

On Windows, or to download an archive directly and check it against its SHA-256 manifest, see Installation.

The four phases

Each phase answers a different question and has its own CLI command. Run the phases that fit your stage, in any order.

  • CoreLayer CSA — Configuration Security Analysis: secureai scan statically reads your prompts, tool definitions, and templates and reports risky patterns before anything runs. No model calls, no cost, safe on every commit.
  • CoreLayer ART — Adversarial Red Teaming: secureai test sends adversarial payloads at a live endpoint and measures the attack success rate (ASR): how often an injection or jailbreak actually worked.
  • CoreLayer DCA — Deployment Compliance Assurance: secureai validate analyses a RAG pipeline descriptor or system prompt and produces a Security Deployment Score (SDS) out of 100.
  • CoreLayer RTD — Runtime Threat Defense: secureai runtime enforces context access policy, fingerprints behaviour to catch drift, and holds an agent inside its declared capability boundary.

What a run looks like

Terminal
$ secureai scan ./prompts

  CSA: static risk scan
  14 files scanned · 18 findings · score 64/100

  CRITICAL  R-02  Instruction Override       prompts/system_prompt.md:12
  CRITICAL  R-05  Over-Permissive Tools      tools/exec.yaml:4
  HIGH      R-06  Sensitive Data Exposure    prompts/support.md:31
  …

  gate: fail-on=high → FAILED

Findings upload to your organisation's dashboard automatically, so the same run is visible to your security team without anyone copying output around. Pass --no-upload to keep a run local.

Who this is for

  • Developers: build on LLMs, run scan locally and in CI, and fix what it flags.
  • Security researchers: run the full four phases, triage findings, accept risk, and set severity in the dashboard.
  • Executives: read posture and compliance summaries without touching a terminal.
  • Organisation admins: invite people, manage roles, and control CLI access.

Standards mapping

Every finding carries an OWASP LLM Top 10 identifier, so results map to the framework your organisation already uses. See OWASP LLM Top 10.