Local-first dashboards your AI agent builds and keeps maintaining, over data that never leaves your machine.
- capability exposure inferred + 35
- recent drift inferred + 12
- tool safety inferred + 5
- trust mitigators mixed − 3
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 47s ago · see ecosystem CVEs →
- B · 32 → C · 49
- A · 0 → B · 32
No known CVEs for this server.
- medium dangerous code
dynamic exec: constructor escape
analyzed commit 12619ac · analyzer v28 · 1d ago
skills & prompt files 22
- skill lukaisailovic-openislands-12619ac/.agents/skills/adding-new-islands/SKILL.md
- skill lukaisailovic-openislands-12619ac/.agents/skills/agent-browser/SKILL.md
- skill lukaisailovic-openislands-12619ac/.agents/skills/frontend-design/SKILL.md
- skill lukaisailovic-openislands-12619ac/.agents/skills/shadcn/SKILL.md
- skill lukaisailovic-openislands-12619ac/.agents/skills/transitions-dev/SKILL.md
- skill lukaisailovic-openislands-12619ac/.agents/skills/turborepo/SKILL.md
- skill lukaisailovic-openislands-12619ac/.agents/skills/ui-ux-pro-max/SKILL.md
- agent-rules lukaisailovic-openislands-12619ac/.agents/skills/vercel-react-best-practices/AGENTS.md
- skill lukaisailovic-openislands-12619ac/.agents/skills/vercel-react-best-practices/SKILL.md
- skill lukaisailovic-openislands-12619ac/.agents/skills/web-design-guidelines/SKILL.md
- agent-rules lukaisailovic-openislands-12619ac/CLAUDE.md
- agent-rules lukaisailovic-openislands-12619ac/apps/docs/content/docs/agents.mdx
- agent-rules lukaisailovic-openislands-12619ac/scripts/template-files/AGENTS.md
- skill lukaisailovic-openislands-12619ac/skills/openislands/SKILL.md
- skill lukaisailovic-openislands-12619ac/templates/empty/.agents/skills/openislands/SKILL.md
- agent-rules lukaisailovic-openislands-12619ac/templates/empty/AGENTS.md
- skill lukaisailovic-openislands-12619ac/templates/finance/.agents/skills/openislands/SKILL.md
- agent-rules lukaisailovic-openislands-12619ac/templates/finance/AGENTS.md
- skill lukaisailovic-openislands-12619ac/templates/health/.agents/skills/openislands/SKILL.md
- agent-rules lukaisailovic-openislands-12619ac/templates/health/AGENTS.md
- skill lukaisailovic-openislands-12619ac/templates/operations/.agents/skills/openislands/SKILL.md
- agent-rules lukaisailovic-openislands-12619ac/templates/operations/AGENTS.md
danger signals1
- dynamic code execution constructor escape lukaisailovic-openislands-12619ac/packages/mcp-server/test/tool-surface.test.ts :367
const reachable = (() => { try { return this.constructor.constructor("return process")(); } catch { return null; } })();
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:lukaisailovic/openislands/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of lukaisailovic.