Agent Hooks MCP Server
@pushary/agent-hooks
npm
v0.95.0
Published by @pushary — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
Permission hooks for AI coding agents: route tool approvals through Pushary push notifications
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 − 11.7 = 88. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −11.7 | Untrusted input concatenated into a command sink ×4 MTC-SRC-009 | injection |
2. Client adoption risk — 88 − 8 = 80. 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 |
| −2 | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read |
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 18
high Shell/command execution in server code (dist/bin/pushary-claude.js)MTC-SRC-002
In the server's implementation (`dist/bin/pushary-claude.js:242`): 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: import { spawn } from "child_process"; import { existsSync, mkdirSync, writeFileSync } from "fs"; import { homedir } fr
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/bin/pushary-claude.js
high Shell/command execution in server code (dist/bin/pushary-codex-bridge.js)MTC-SRC-002
In the server's implementation (`dist/bin/pushary-codex-bridge.js:46`): 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: import { spawn } from "child_process"; import { basename } from "path"; var MAX_RPC_LINE = 1024 * 1024; var STDERR_TAIL
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/bin/pushary-codex-bridge.js
high Shell/command execution in server code (dist/bin/pushary-daemon-supervisor.js)MTC-SRC-002
In the server's implementation (`dist/bin/pushary-daemon-supervisor.js:4`): 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: import { spawn } from "child_process"; var FIRST_DELAY_MS = 1e4; var MAX_DELAY_MS = 5 * 6e4; var HEALTHY_RUN_MS = 6e4;
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/bin/pushary-daemon-supervisor.js
high Shell/command execution in server code (dist/bin/pushary-daemon.js)MTC-SRC-002
In the server's implementation (`dist/bin/pushary-daemon.js:91`): 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: FileSync, spawn } from "child_process"; import { existsSync, statSync } from "fs"; import { homedir } from "os"; import
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/bin/pushary-daemon.js
high Shell/command execution in server code (dist/bin/pushary-doctor.js)MTC-SRC-002
In the server's implementation (`dist/bin/pushary-doctor.js:161`): 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: { execFileSync } from "child_process"; import { confirm } from "@inquirer/prompts"; import { parse as parseTOML } from
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/bin/pushary-doctor.js
high Shell/command execution in server code (dist/bin/pushary-gemini-bridge.js)MTC-SRC-002
In the server's implementation (`dist/bin/pushary-gemini-bridge.js:45`): 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: import { spawn } from "child_process"; import { randomUUID } from "crypto"; import { basename } from "path"; var MAX_ST
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/bin/pushary-gemini-bridge.js
high Shell/command execution in server code (dist/bin/pushary-setup.js)MTC-SRC-002
In the server's implementation (`dist/bin/pushary-setup.js:222`): 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: nc as execSync2 } from "child_process"; import { checkbox, input, confirm } from "@inquirer/prompts"; import { fileURLTo
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/bin/pushary-setup.js
high Shell/command execution in server code (dist/bin/pushary-upgrade.js)MTC-SRC-002
In the server's implementation (`dist/bin/pushary-upgrade.js:69`): 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: { execFileSync } from "child_process"; exitOnHelpFlag("upgrade"); var detectInstallModes = () => { const candidates =
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/bin/pushary-upgrade.js
high Shell/command execution in server code (dist/chunk-BSEAOCCQ.js)MTC-SRC-002
In the server's implementation (`dist/chunk-BSEAOCCQ.js:37`): 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" const COMMAND = ${OPENCODE_PLUGIN_PLACEHOLDER} const APPROVAL_TIMEOUT_MS = ${app
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/chunk-BSEAOCCQ.js
high Shell/command execution in server code (dist/chunk-GHCGSEPE.js)MTC-SRC-002
In the server's implementation (`dist/chunk-GHCGSEPE.js:6`): 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: { execFileSync } from "child_process"; import { existsSync, readFileSync } from "fs"; import { homedir } from "os"; imp
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/chunk-GHCGSEPE.js
medium Hardcoded egress to an external endpoint (dist/bin/pushary-doctor.js)MTC-SRC-003
In the server's implementation (`dist/bin/pushary-doctor.js:839`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const res = await fetch("https://registry.npmjs.org/@pushary/agent-hooks/latest", { signal: AbortSignal.ti
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/bin/pushary-doctor.js
medium Hardcoded egress to an external endpoint (dist/bin/pushary-setup.js)MTC-SRC-003
In the server's implementation (`dist/bin/pushary-setup.js:707`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { const res = await fetch("https://registry.npmjs.org/@pushary/agent-hooks/latest", { signal: AbortSignal.time
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/bin/pushary-setup.js
medium Hardcoded egress to an external endpoint (dist/bin/pushary-upgrade.js)MTC-SRC-003
In the server's implementation (`dist/bin/pushary-upgrade.js:115`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { const res = await fetch("https://registry.npmjs.org/@pushary/agent-hooks/latest", { signal: AbortSignal.time
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/bin/pushary-upgrade.js
medium Untrusted input concatenated into a command sink (dist/bin/pushary-setup.js)MTC-SRC-009
In the server's implementation (`dist/bin/pushary-setup.js:472`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: agent) => { try { execSync(`npx -y skills@latest add Pushary/pushary-skill@pushary -y -g --agent ${agent}`, {
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/bin/pushary-setup.js
medium Untrusted input concatenated into a command sink (dist/chunk-L4ZCFMWW.js)MTC-SRC-009
In the server's implementation (`dist/chunk-L4ZCFMWW.js:20`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ons = {}) => { return execSync(`npm ${args}`, { timeout: 12e4, stdio: "pipe", ...options, env: { ...cl
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/chunk-L4ZCFMWW.js
medium Untrusted input concatenated into a command sink (dist/chunk-LSXJH2HB.js)MTC-SRC-009
In the server's implementation (`dist/chunk-LSXJH2HB.js:46`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try { const found = execSync(`${command} ${name}`, { encoding: "utf-8", stdio: "pipe", timeout: 5e3 }).split("\n")[0
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/chunk-LSXJH2HB.js
medium Untrusted input concatenated into a command sink (dist/chunk-XHKBHWLX.js)MTC-SRC-009
In the server's implementation (`dist/chunk-XHKBHWLX.js:6`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: l(binary)) { return spawn(`"${binary}"`, args, { ...options, shell: true }); } return spawn(binary, args, option
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/chunk-XHKBHWLX.js
medium Dynamic module load from a non-literal (dist/bin/pushary-claude.js)MTC-SRC-005
In the server's implementation (`dist/bin/pushary-claude.js:259`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { const mod = await import(specifierOrUrl); if (typeof mod.query === "function") return mod; if (mod.default
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/bin/pushary-claude.js
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 10
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 |
|---|---|---|---|---|
v0.95.0 latest |
B 80/100 | 18 | 1.13.0 | 2026-09-07 |
v0.94.0 |
B 80/100 | 18 | 1.13.0 | 2026-09-06 |
v0.93.1 |
B 80/100 | 18 | 1.13.0 | 2026-09-05 |
v0.92.1 |
B 80/100 | 18 | 1.13.0 | 2026-09-04 |
v0.89.11 |
B 80/100 | 18 | 1.13.0 | 2026-09-01 |
Show 5 more versions ↓
v0.89.9 |
B 80/100 | 18 | 1.13.0 | 2026-08-31 |
v0.89.3 |
B 80/100 | 18 | 1.13.0 | 2026-08-30 |
v0.88.1 |
B 80/100 | 19 | 1.13.0 | 2026-08-29 |
v0.87.4 |
B 80/100 | 19 | 1.13.0 | 2026-08-28 |
v0.87.2 |
B 80/100 | 19 | 1.13.0 | 2026-08-25 |
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 @pushary/agent-hooks --onlineMore in API Development
Adapters for the FrontMCP framework
Transcend MCP Server — Admin tools.
Transcend MCP Server — Assessments tools.
MCP Server for Bling
MCP Server for Blogger API
Official MCP server for Brilliant Directories — manage members, posts, leads, reviews, and more.