Local-first non-linear memory OS for AI operators. One index across Claude Code, Codex, Cursor, Windsurf, Hermes, OpenCode, Aider, pi, and more — with an editable timeline.
- capability exposureinferred+35
- trust mitigatorsmixed−3
inferredmixed
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 15m ago · see ecosystem CVEs →
No known CVEs for this server.
- highdangerous code
env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (/tmp/obs-code-0LbHrO/pbmagnet4-nlm
analyzed commit dda6d28 · analyzer v17 · 3d ago
danger signals1
- suspicious endpointapi.telegram.orgpbmagnet4-nlm-memory-dda6d28/src/cli/digest.ts:131
const url = `https://api.telegram.org/bot${token}/sendMessage`;
[](https://mcpobservatory.com/servers/github:pbmagnet4/nlm-memory/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 pbmagnet4.