Operational guardrails for AI agents
- capability exposure inferred + 35
- recent drift inferred + 20
- tool safety inferred + 12
inferred
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.
grade last moved 3d ago · see ecosystem CVEs →
- C · 59 → D · 67
- C · 56 → C · 59
- A · 0 → C · 56
No known CVEs for this server.
- high dangerous code
dynamic exec: vm exec
analyzed commit 6019bec · analyzer v33 · 17h ago
danger signals2
- dynamic code execution vm exec ARKTechSolutions-mandate-os-6019bec/packages/mandate-os-openclaw/assets/plugin/index.cjs :152
const parsed = vm.runInNewContext(`(${raw})`, Object.create(null), { - dynamic code execution vm exec ARKTechSolutions-mandate-os-6019bec/packages/mandate-os-openclaw/src/openclaw-setup.ts :970
const parsed = vm.runInNewContext(`(${raw})`, Object.create(null), {
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:ARKTechSolutions/mandate-os/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 ARKTechSolutions.