agent-hooks@1.9.120
VERIFIED· not startedPublisher 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.
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: Verified 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_KEYor--with-tokenConfiguration, not credentials: CLAIM_PATH, CLAUDE_CONFIG_DIR, CLIENT_REPORT_PATH, DEVICE_KEY_PATH, DISPLAY, EPISODE_PATH, GEMINI_CLI_HOME, GROK_SESSION_ID, MACHINES_PATH, OPENCODE_CONFIG_DIR, PLUGIN_LOCATIONS_KEY, 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_NO_BROWSER, PUSHARY_PIN_GLOBAL_VERSION, PUSHARY_RECIPIENT_PIN_FILE, PUSHARY_RESPECT_PERMISSION_MODE, PUSHARY_SESSION_KEY_DIR, PUSHARY_SUPPRESS_KEY_DRIFT_WARNING, PUSHARY_TRANSCRIPT_REGISTRY_DIR, PUSHARY_WRAPPER_ACTIVE, REUSED_KEY_SOURCE_LABELS, SELF_REVOKE_PATH, SPARED_KEY_WHY, SSH_TTY, START_PATH, WAYLAND_DISPLAY- Where it talks to
- pushary.com (its own)Also nodejs.org, apple.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 nodejs.org, apple.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.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
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 2026-11-09 and scored it 83/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 2 s · 2 scenarios · 0 deviationsStatic findings
var skillsCliCommand = (agent, nodeVersion) => `npx -y skills@${skillsCliVersionForNode(nodeVersion)} add ${PUSHARY_SKILL_SOURCE}@${PUSHARY_SKILL_NAME} -y -g --agent ${agent}`;Fix: Pin versions and sources; vendor anything fetched at install time.const previous = readAutoUpdateState(context.statePath);Fix: Pin versions and sources; vendor anything fetched at install time.' [ -e "$left" ] && ! kill -0 "${left##*.}" 2>/dev/null && rm -f "$left"',Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.…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.const state = recordAutoUpdateCheck(run.statePath ?? autoUpdateState(), { result: "failed", detail: claim.reason }, at);Fix: Pin versions and sources; vendor anything fetched at install time.if (mode?.kill || mode?.mode === "terminal_only") return;Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.recordAutoUpdateCheck(context.statePath, pending, new Date(context.now()).toISOString());Fix: Pin versions and sources; vendor anything fetched at install time.console.log(` ${dim("A browser on this computer is subscribed, but no phone is connected yet.")}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.appendAutoUpdateLog(context.logPath, `${new Date(context.now()).toISOString()} installing ${context.location.packageName}@${latest} into ${context.location.prefix}`);Fix: Pin versions and sources; vendor anything fetched at install time."ask Add Pushary instructions to this project's CLAUDE.md/AGENTS.md? (default no)",Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
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
No advisories in OSV for @pushary/agent-hooks@1.9.120 as of 5d ago. This is the package itself, not its dependencies.