Codex Agent Session Manager MCP Server
codex-agent-session-manager
npm
v0.1.0-alpha.9
Source verified
Published by apethor — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 6 = 94. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 10
high Shell/command execution in server code (dist/init.js)MTC-SRC-002
In the server's implementation (`dist/init.js:531`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: spawnSync } from 'node:child_process'; const shellDir = dirname(fileURLToPath(import.meta.url)); const managerDir = re
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/init.js
high Shell/command execution in server code (dist/npm.js)MTC-SRC-002
In the server's implementation (`dist/npm.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: spawnSync } from 'node:child_process'; import { existsSync } from 'node:fs'; import { win32 as win32Path } from 'node:p
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/npm.js
high Shell/command execution in server code (dist/processes.js)MTC-SRC-002
In the server's implementation (`dist/processes.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: spawnSync } from 'node:child_process'; import { resolve } from 'node:path'; import { redactSensitiveText } from './secu
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/processes.js
high Shell/command execution in server code (dist/remote.js)MTC-SRC-002
In the server's implementation (`dist/remote.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: spawnSync } from 'node:child_process'; import { createHash, randomInt } from 'node:crypto'; import { closeSync, copyFil
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/remote.js
low Shell/command execution in packaging/dev tooling (dist/tools/app-server-lifecycle.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/tools/app-server-lifecycle.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from 'node:child_process'; import { z } from 'zod'; import { appServerRuntimeCompatibility, appServerStateF
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/tools/app-server-lifecycle.js
low Shell/command execution in packaging/dev tooling (dist/tools/app-server-start.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/tools/app-server-start.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from 'node:child_process'; import { z } from 'zod'; import { buildRemotePlan, executeRemotePlan, remotePlan
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/tools/app-server-start.js
low Shell/command execution in packaging/dev tooling (dist/tools/mcp-refresh.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/tools/mcp-refresh.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from 'node:child_process'; import { z } from 'zod'; import { connectAppServerClient } from '../app-server/c
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/tools/mcp-refresh.js
low Shell/command execution in packaging/dev tooling (dist/tools/reload.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/tools/reload.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from 'node:child_process'; import { z } from 'zod'; import { connectAppServerClient } from '../app-server/c
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/tools/reload.js
low Shell/command execution in packaging/dev tooling (dist/tools/session-close.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/tools/session-close.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from 'node:child_process'; import { z } from 'zod'; import { resolveAppServerUrl } from '../app-server/conf
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/tools/session-close.js
low Shell/command execution in packaging/dev tooling (dist/tools/session-continue.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/tools/session-continue.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from 'node:child_process'; import { z } from 'zod'; import { connectAppServerClient } from '../app-server/c
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/tools/session-continue.js
Tools 26
Each tool and what it can reach — statically extracted from the published source.
codex_app_server_startno sensitive capabilitycodex_app_server_state_readno sensitive capabilitycodex_app_server_statusno sensitive capabilitycodex_app_server_stopno sensitive capabilitycodex_global_mcp_add_npmno sensitive capabilitycodex_global_mcp_removeno sensitive capabilitycodex_local_mcp_add_npmno sensitive capabilitycodex_local_mcp_removeno sensitive capabilitycodex_mcp_cleanup_reportno sensitive capabilitycodex_mcp_install_npmno sensitive capability
Show 16 more tools ↓
codex_mcp_package_inspectno sensitive capabilitycodex_mcp_refreshno sensitive capabilitycodex_mcp_reloadno sensitive capabilitycodex_mcp_status_listno sensitive capabilitycodex_operation_readno sensitive capabilitycodex_operation_waitno sensitive capabilitycodex_secret_statusno sensitive capabilitycodex_session_closeno sensitive capabilitycodex_session_continueno sensitive capabilitycodex_session_hard_relaunchno sensitive capabilitycodex_session_launchno sensitive capabilitycodex_session_manager_helpno sensitive capabilitycodex_session_manager_probeno sensitive capabilitycodex_session_replaceno sensitive capabilitycodex_thread_contextno sensitive capabilitycodex_threads_listno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (26 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.1.0-alpha.9 latest |
A 94/100 | 10 | 1.8.0 | 2026-07-23 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan codex-agent-session-manager --onlineMore in Developer Tools
Security scan results for the 1stay MCP server.
Security scan results for the Adguard Home MCP server.
Security scan results for the Ado Browser MCP server.
Security scan results for the Adobe Experience Dev MCP server.
Security scan results for the Aemet MCP server.
Security scan results for the Affinity Mcp Bridge MCP server.