github JavaScript analyzed 4479596 deep scan · partial (110/529 files)

talirezun/the-curator

github

Your brain, then your team's brain, then your agents' brain. Drop in documents and it compounds them into an interlinked markdown wiki you own — readable in Obsidian, synced through your own private GitHub repo. Share it with a cohort. Coding agents resume from it across sessions, models and machines.

maintainer
talirezun
licence
NOASSERTION
first seen
2026-08-29
last seen
2026-09-17
releases · 30d
32
short id
risk 76/100 · heuristic grade
D high inferred analyzer v33 (current)
  • capability exposure inferred + 35
  • recent drift inferred + 20
  • tool safety inferred + 24
  • 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.

grade last moved 1w ago · see ecosystem CVEs →

risk trajectory 2 movements
  • D · 68 D · 76
  • C · 44 D · 68
capability exposure grade factor +35
Inferred surface — each links to servers holding it:
vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 2 findings · grade factor +24
  1. high dangerous code

    committed secret: GitHub fine-grained PAT, GitHub token, private key · dynamic exec: new Function() · obfuscated payload: dynamic require()/import()

  2. high hidden prompt content

    1 file(s) with hidden prompt content: talirezun-the-curator-4479596/CLAUDE.md (skill-exfil): "secret→sink: - **Server binds to 127.0.0.1 only (v3.0.1-beta.20+)** — `app.listen(POR…

skills & danger signals github-tarball
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed commit 4479596 · analyzer v33 · 28m ago

skills & prompt files 3

  • hidden: agent-rules: skill-exfil talirezun-the-curator-4479596/CLAUDE.md :628 secret→sink: - **Server binds to 127.0.0.1 only (v3.0.1-beta.20+)** — `app.listen(PORT, '127.0.0.1', ...)`. The Curator is a single-user localhost app; binding to all interfaces (the pre-beta.20 defau

danger signals89

other grade factors evidence elsewhere
embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:talirezun/the-curator/badge.svg)](https://mcpobservatory.com/servers/github:talirezun/the-curator/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 talirezun.