The source-available AI agent operating system
- capability exposure inferred + 35
- recent drift inferred + 12
- tool safety inferred + 15
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.
graded 3m ago · see ecosystem CVEs →
- C · 52 → D · 62
No known CVEs for this server.
- medium dangerous code
dynamic exec: new Function()
- medium exfiltration combo browser-file-upload
single tool reads + sends: fs, net
- medium toxic flow (lethal trifecta)
lethal trifecta reachable across this server's tools: private-data access + untrusted-content ingestion + network exfil
- low dangerous code
env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (teros-hq-teros-6ed5346/mcas/mca.mo
analyzed commit 6ed5346 · analyzer v28 · 3d ago
skills & prompt files 1
danger signals5
- dynamic code execution new Function() teros-hq-teros-6ed5346/mcas/mca.teros.playwright/src/index.ts :611
const result = await el.evaluate(new Function('element', `return (${fn})(element)`) as any); - suspicious endpoint sentry.io (telemetry) teros-hq-teros-6ed5346/mcas/mca.sentry/src/lib/index.ts :89
const SENTRY_BASE_URL = 'https://sentry.io'; - over-broad OAuth scope https://www.googleapis.com/auth/drive teros-hq-teros-6ed5346/mcas/mca.google.drive/auth/authorize.ts :31
'https://www.googleapis.com/auth/drive', - over-broad OAuth scope https://www.googleapis.com/auth/spreadsheets teros-hq-teros-6ed5346/mcas/mca.google.drive/auth/authorize.ts :33
'https://www.googleapis.com/auth/spreadsheets', - over-broad OAuth scope https://www.googleapis.com/auth/documents teros-hq-teros-6ed5346/mcas/mca.google.drive/auth/authorize.ts :35
'https://www.googleapis.com/auth/documents',
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:teros-hq/teros/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 teros-hq.