Your personal AI runtime, local-first. Patchwork OS gives any AI model a consistent set of tools, YAML recipes, a delegation policy with approval queue, and a durable trace memory — all on your machine, all under your policy.
- capability exposure inferred + 35
- supply-chain attested + 6
- trust mitigators mixed − 9
attested 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 9m ago · see ecosystem CVEs →
- C · 38 → B · 32
- B · 32 → C · 38
- C · 44 → B · 32
- C · 50 → C · 44
- C · 44 → C · 50
- C · 56 → C · 44
- 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. (package/dist/connectors/airtable.j
- 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. (package/dist/index.js:3825)
- 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. (package/dist/recipes/yamlRunner.js
analyzed v1.2.0-beta.2 · analyzer v31 · 1d ago
skills & prompt files 4
danger signals3
- suspicious endpoint us.posthog.com (telemetry) package/dist/connectors/posthog.js :17
const DEFAULT_POSTHOG_HOST = "https://us.posthog.com"; - suspicious endpoint api.telegram.org package/dist/connectors/telegram.js :24
const TELEGRAM_BASE = "https://api.telegram.org"; - suspicious endpoint my-org.sentry.io (telemetry) package/dist/recipes/tools/sentry.js :25
description: "Sentry issue ID (e.g., '4567890123') or full URL (e.g., 'https://my-org.sentry.io/issues/4567890123/'). Org slug is inferred from the URL when present.",
- supply-chain +6 supply-chain hub →
[](https://mcpobservatory.com/servers/npm:patchwork-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 oolab-labs.