Skills/npm/agent-hooks

agent-hooks@1.9.187

CAUTION· not started

Publisher claims: "Human-in-the-loop (HITL) for AI agents: ask a person for approvals or answers by push notification. One command connects Claude Code, Codex, Cursor, Gemini CLI and more." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher pushary · publishing for 194 daysInstalls 22,211Last detonated 15 min ago

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
PUSHARY_API_KEY or --no-ask-passwordConfiguration, not credentials: CLAIM_PATH, CLAUDE_CONFIG_DIR, CLIENT_REPORT_PATH, CODEX_EVENT_KEY, CODEX_HOME, DEVICE_KEY_PATH, DISPLAY, EPISODE_PATH, GROK_SESSION_ID, HERMES_COMMAND_ALLOWLIST_KEY, HERMES_GATE_TOOLS_KEY, IDENTITY_PATH, OPENCODE_CONFIG_DIR, PATHEXT, PLUGIN_LOCATIONS_KEY, ProgramFiles, ProgramW6432, PUSHARY_ADMISSION_FILE, PUSHARY_API_URL, PUSHARY_APP_REGISTER_TIMEOUT_MS, PUSHARY_BASE_URL, PUSHARY_BELL_QUIET, PUSHARY_BELL_UPGRADE_AT, PUSHARY_CLAUDE_BIN, PUSHARY_CONFIG_FILE, PUSHARY_DEFER_BYPASS, PUSHARY_LEDGER_FILE, PUSHARY_MCP_PATH_PREFIX, PUSHARY_NO_BROWSER, PUSHARY_RESPECT_PERMISSION_MODE, PUSHARY_SUPPRESS_KEY_DRIFT_WARNING, REUSED_KEY_SOURCE_LABELS, SELF_REVOKE_PATH, SSH_TTY, START_PATH, USERDOMAIN, USERNAME, WAYLAND_DISPLAY, WSL_DISTRO_NAME
Where it talks to
pushary.com (its own)Also apple.com, nodejs.org, microsoft.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names apple.com, nodejs.org, microsoft.com as well as its own vendor. The guard injects PUSHARY_API_KEY only into requests to pushary.com (and its subdomains) and refuses the rest.

$vet-skills run --secrets PUSHARY_API_KEY=pushary.com -- npx -y @pushary/agent-hooks

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 1.9.141

vet-skills diff agent-hooks 1.9.141 1.9.187

In the sandbox, this version reached for nothing 1.9.141 did not. Compared from the two recorded runs, not from source.

No longer contacted
claude.ai, discord.gg

1.9.141 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-18 and scored it 72/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Auto-update or dynamic fetch configuration; Access to sensitive file paths; Auto-update or dynamic fetch configuration. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 2 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
1.8sprocessdependency install exit 1 · npm error code EUNSUPPORTEDPROTOCOL npm error Unsupported URL Type "workspace:": workspace:* npm error A complete log of this run can be found in: /tmp/ks-detonate-y9TkcD/task/home/.npm/_logs/2026-11-18T16_36_56_152Z-debug-0.log
1.8sclaimednot started: dependency install failed (exit 1); the server itself was not observed
1.8sprocessscript backend runs setup only
1.8sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actiondist/chunk-52CIHAC2.js:828 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` ${dim('This computer keeps its own key. Revoke the extra "Paired agent (mobile)" key at')} ${cyan("pushary.com/dashboard/agent/settings")}${dim(".")}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Auto-update or dynamic fetch configurationdist/chunk-2PQY4TMQ.js:105 · Auto-update or dynamic fetch configuration — agent may load new code at runtimevar autoUpdateReportState = (decision) => {Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsdist/chunk-BWOQACK7.js:1245 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesvar ENVIRONMENT_FILE_NAME = ".env";Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Auto-update or dynamic fetch configurationdist/chunk-2PQY4TMQ.js:98 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeconst offReason = autoUpdateOffReason(input);Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Privileged sudo commanddist/chunk-AIZYJJGD.js:83 · Privileged sudo command — agent may execute with elevated privilegesreturn `no: it ${STOPS_AT_LOGOUT}; run \`pushary daemon install\`, or \`sudo loginctl enable-linger $USER\``;Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)dist/chunk-BWOQACK7.js:814 · MCP server using network transport (SSE/HTTP) — data sent over network…ray(value)) return false; const snapshot = value; return typeof snapshot.hadMcpServers === "boolean" && typeof snapshot.mcpServersWasRecord === "boolean" && (!snapshot.hadMcpServers || snapshot.mcpServersWasRecord || Object.hasOwn(snapshot…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Process kill commanddist/chunk-4OSTVMM5.js:1157 · Process kill command — agent can terminate processesif (mode?.kill || mode?.mode === "terminal_only") return;Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Auto-update or dynamic fetch configurationdist/chunk-BWOQACK7.js:1299 · Auto-update or dynamic fetch configuration — agent may load new code at runtimevar autoUpdateState = () => join7(pusharyDir(), "auto-update.json");Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commanddist/chunk-L3BX56Y4.js:1032 · Process kill command — agent can terminate processes' [ -e "$left" ] && ! kill -0 "${left##*.}" 2>/dev/null && rm -f "$left"',Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagedist/chunk-2IBCLVJK.js:535 · npx invocation of non-well-known package — may execute untrusted code…unsFromATemporaryFolder(entry)) say("This copy of Pushary runs from a temporary npx folder. If that folder is cleared, the cards stop reaching Pushary and Codex keeps work…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiondist/chunk-52CIHAC2.js:301 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` ${dim("A browser on this computer is subscribed, but no phone is connected yet.")}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Auto-update or dynamic fetch configurationdist/chunk-2PQY4TMQ.js:102 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeif (checkedWithinInterval(input.state.lastCheckAt, input.now, autoUpdateCheckInterval(input.state))) return { kind: "skip", reason: "checked_recently" };Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationdist/chunk-2PQY4TMQ.js:96 · Auto-update or dynamic fetch configuration — agent may load new code at runtimevar autoUpdateDecision = (input) => {Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationdist/chunk-2PQY4TMQ.js:60 · Auto-update or dynamic fetch configuration — agent may load new code at runtimevar autoUpdateOffReason = (input) => {Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Privileged sudo commanddist/chunk-AIZYJJGD.js:76 · Privileged sudo command — agent may execute with elevated privilegestext: `Phone-start ${STOPS_AT_LOGOUT}. To keep it running: \`sudo loginctl enable-linger ${outcome.user}\``Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/chunk-D35DKI3E.js:196 · Process kill command — agent can terminate processes…ools (grep, list_dir, glob, read_file, todo_write, search_tool) only honour the kill switch and a deny rule, as Claude Code's reads do. Grok fails open if it kills t…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈81 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.

What would make this Verified

8 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim pushary: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  6. MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim pusharyPropose a patch to the maintainer