github JavaScript analyzed 22a36fb

SethGammon/Citadel

The operating layer for Claude Code + OpenAI Codex: persistent project memory, intent routing, safety hooks, cost telemetry, and parallel agent fleets.

maintainer: SethGammon
licence: MIT
first seen: 2026-06-12
last seen: 2026-09-14
releases · 30d: 4
short id

risk 51/100 · heuristic grade

C elevated inferred analyzer v33 (current)

vulnerabilities attested + 7
capability exposure inferred + 35
tool safety inferred + 12
trust mitigators mixed − 3

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.

grade last moved 1w ago · see ecosystem CVEs →

risk trajectory 6 movements

2w ago C · 44 → C · 51
5w ago D · 64 → C · 44
5w ago C · 56 → D · 64
6w ago B · 32 → C · 56
9w ago C · 35 → B · 32
12w ago A · 0 → C · 35

capability exposure grade factor +35

Inferred surface — each links to servers holding it:

vulnerabilities 1 CVEs · grade factor +7

MEDIUM

Path traversal / arbitrary file read in the context-compress MCP server (smart_read) bypasses prote… affects ["<= 1.0.0"]

tool safety 1 findings · grade factor +12

high dangerous code

dynamic exec: vm exec · obfuscated payload: dynamic require()/import()

skills & danger signals github-tarball

prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed commit 22a36fb · analyzer v33 · 14h ago

skills & prompt files 53

danger signals3

dynamic code execution vm exec SethGammon-Citadel-22a36fb/scripts/test-demo.js :45 route = vm.runInNewContext(routeBlock + '\nroute;', {});
dynamic code execution vm exec SethGammon-Citadel-22a36fb/scripts/test-runtime-registry.js :185 vm.runInNewContext(source, {
dynamic code execution vm exec SethGammon-Citadel-22a36fb/scripts/test-version-upgrades.js :38 vm.runInNewContext(fs.readFileSync(path.join(repo, 'core/forks/claude-launcher.js'), 'utf8'), context);

embed badge readme-ready

[![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:SethGammon/Citadel/badge.svg)](https://mcpobservatory.com/servers/github:SethGammon/Citadel/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 SethGammon.

SethGammon/Citadel

skills & prompt files 53

danger signals3

Navigate

Stream

Features

Display