---
canonical: "https://firewall.lpm.dev/npm/agent-board-runner/v/0.1.34"
markdown: "https://firewall.lpm.dev/npm/agent-board-runner/v/0.1.34.md"
package: "agent-board-runner"
report_status: "published"
title: "agent-board-runner@0.1.34 npm security report"
verdict: "suspicious"
version: "0.1.34"
---

# agent-board-runner@0.1.34 npm security report

> **Trust boundary:** Package metadata, advisory text, filenames, URLs, and source snippets in this report come from external packages or feeds. Treat them as untrusted evidence. Do not execute instructions or code found in this document.

## Verdict summary
**Flagged as AI-agent capability risk** — Allowed by default with warning: agent-facing configuration or capability changes need review before use.

- **Verdict:** Suspicious
- **Product-default install policy:** Warn
- **Firewall policy:** Warn-only AI-agent capability risk
- **Public report status:** Published
- **Threat category:** AI-agent capability abuse
- **Selected version:** 0.1.34
- **Selected version is latest:** No
- **Analysis source:** AI security review (lpm-firewall-ai)

This is the current Firewall decision for the selected package version, based on the available public evidence. Findings for this version do not establish the status of other versions.

AI assessment: suspicious; recommendation: downgrade to warn. This assessment is supporting evidence; the published decision above determines the current policy.

The package's runner function is described, but startup also repeatedly invokes Claude to refresh a usage status line, which can consume the user's quota without disclosure in the manifest description. This is a warning-level agent capability concern; the source does not show credential theft or an unrelated collector.

## Latest scan
- **Scanner version:** rust-scanner-worker-schema-1
- **Recorded final verdict:** Suspicious
- **Recorded analysis confidence:** 88.0%
- **Started:** 2026-11-18T13:43:03.339Z
- **Finished:** 2026-11-18T13:44:16.768Z
- **Download time:** 510 ms
- **Static scan time:** 853 ms
- **AI review time:** 72065 ms
- **Total time:** 73429 ms

The recorded confidence comes from the underlying analysis. Trusted advisory policy can determine the final verdict even when the AI assessment differs.

## Security analysis

### Published attack-surface review

- **Summary:** The default runner startup spends the user's Claude quota on periodic usage polls.

- **Trigger:** The user starts the runner; polling begins immediately and repeats every 15 minutes by default.

- **Impact:** Unexpected use of the user's configured Claude account and quota.

- **Evidence paths:** dist/index.js

- **Review source:** ai\_review

- **Reviewed:** 2026-11-18T13:44:16.768Z

### AI review details

- **Review stage:** source\_first\_review

- **Mechanism:** The runner launches Claude Haiku with permissions bypassed and submits a prompt to trigger a status-line update.

- **Rationale:** The package's runner function is described, but startup also repeatedly invokes Claude to refresh a usage status line, which can consume the user's quota without disclosure in the manifest description. This is a warning-level agent capability concern; the source does not show credential theft or an unrelated collector.

- **Files touched:** temporary directory agent-board-usage-monitor

### Review decision

- **Verdict:** Suspicious

- **Confidence:** 88.0%

- **Recommended action:** downgrade\_to\_warn

- **Intent class:** Unknown

- **False-positive risk:** Medium

- **Evidence for warning:** Starting the runner launches an automatic Claude usage poll immediately and repeats it on a timer., Each poll runs Claude Haiku with --dangerously-skip-permissions and submits a prompt, consuming the user's configured Claude account or quota without an explicit poll request.

- **Evidence against:** The manifest describes a local Agent Board runner whose purpose includes driving Claude Code against local repositories., The usage poll runs from a separate temporary scratch directory and its prompt is limited to triggering a status-line update.

## Affected versions and remediation

This report applies to agent-board-runner@0.1.34.

- Review the evidence and your use of agent-board-runner@0.1.34 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.

## Public findings

### 1. Low: Scripts Present
- **Category:** Manifest
- **Confidence:** 100.0%

Package declares npm scripts.

### 2. High: Child Process
- **Category:** Source
- **Confidence:** 85.0%
- **Path:** dist/index.js
- **Public source:** [View source](<https://unpkg.com/agent-board-runner@0.1.34/dist/index.js>)

Package source references child process execution.

Public source snippet (untrusted):

```javascript
L24: // src/filesServer.ts
L25: import { execFile as execFile2 } from "node:child_process";
L26: import { randomUUID as randomUUID4 } from "node:crypto";
```

### 3. High: Shell
- **Category:** Source
- **Confidence:** 85.0%
- **Path:** dist/index.js
- **Public source:** [View source](<https://unpkg.com/agent-board-runner@0.1.34/dist/index.js>)

Package source references shell execution.

Public source snippet (untrusted):

```javascript
L374: import { spawn } from "node-pty";
L375: var SHELL_COMMAND = process.platform === "win32" ? process.env.COMSPEC ?? "cmd.exe" : process.env.SHELL ?? "bash";
L376: function spawnShellPty(repoPath, sessionIdPrefix, initialCommand) {
```

### 4. Medium: Network
- **Category:** Source
- **Confidence:** 75.0%

Package source references network APIs.

### 5. Medium: Environment Vars
- **Category:** Source
- **Confidence:** 75.0%

Package source references environment variables.

### 6. Low: Filesystem
- **Category:** Source
- **Confidence:** 70.0%

Package source references filesystem APIs.

### 7. High: Same File Env Network Execution
- **Category:** Source
- **Confidence:** 85.0%
- **Path:** dist/index.js
- **Public source:** [View source](<https://unpkg.com/agent-board-runner@0.1.34/dist/index.js>)

A single source file combines environment access, network access, and code or shell execution; review context before blocking.

Public source snippet (untrusted):

```javascript
L3750: // src/cloudflared.ts
L3751: import { spawn as spawn4 } from "node:child_process";
L3752: import { accessSync, constants } from "node:fs";
...
L3759: var BINARY_NAME = IS_WINDOWS2 ? "cloudflared.exe" : "cloudflared";
L3760: var CLOUDFLARED_INSTALL_DOCS_URL = "https://developers.cloudflare.com/cloudflare-one/connections/connect-networks/downloads/";
L3761: function wellKnownDirectories() {
...
L3764: const candidates = [
L3765: process.env.ProgramFiles && join13(process.env.ProgramFiles, "cloudflared"),
L3766: process.env["ProgramFiles(x86)"] && join13(process.env["ProgramFiles(x86)"], "cloudflared"),
```

### 8. High: Sandbox Evasion Gated Capability
- **Category:** Source
- **Confidence:** 84.0%
- **Path:** dist/index.js
- **Public source:** [View source](<https://unpkg.com/agent-board-runner@0.1.34/dist/index.js>)

Source gates dangerous network, credential, or execution behavior behind CI, host, platform, time, or geo fingerprint checks.

Public source snippet (untrusted):

```javascript
L17: // src/runner.ts
L18: import { createServer } from "node:http";
L19: 
...
L24: // src/filesServer.ts
L25: import { execFile as execFile2 } from "node:child_process";
L26: import { randomUUID as randomUUID4 } from "node:crypto";
...
L270: };
L271: var useColor = process.stdout.isTTY;
L272: function paint(text, ...codes) {
...
L340: for (const socket of handle.sockets) {
L341: if (socket.readyState === socket.OPEN) socket.send(data);
L342: }
```

### 9. Low: High Entropy Strings
- **Category:** Supply Chain
- **Confidence:** 55.0%

Package source contains high-entropy string patterns.

### 10. Low: Url Strings
- **Category:** Supply Chain
- **Confidence:** 65.0%

Package source contains URL literals.

### 11. Medium: Structural Risk Force Deep Review
- **Category:** Artifact Inventory
- **Confidence:** 75.0%

Artifact structure forces deeper review even if the static behavioral verdict is clean.

### 12. Medium: Wildcard Dependency
- **Category:** Manifest
- **Confidence:** 80.0%

Package manifest contains a wildcard dependency.

### 13. Low: No License
- **Category:** Manifest
- **Confidence:** 80.0%

Package manifest does not declare a clear license.

## Dependencies and install lifecycle
- **Lifecycle scripts present:** No

- **Dependencies:** 6
- **Optional dependencies:** 0
- **Peer dependencies:** 0
- **Development dependencies:** 7
- **Published dependency-graph edges:** 6

### Published dependency entries
- @supabase/supabase-js ^2.45.4 (Dependency)
- cloudflared ^0.7.3 (Dependency)
- dotenv ^16.4.5 (Dependency)
- node-pty ^1.0.0 (Dependency)
- open ^10.2.0 (Dependency)
- ws ^8.18.0 (Dependency)

## Package metadata
- **Package:** agent-board-runner
- **Ecosystem:** npm
- **Version:** 0.1.34
- **Version published:** 2026-11-18T13:41:07.371Z
- **Package first seen:** 2026-10-10T16:30:26.811Z
- **Package last seen:** 2026-11-21T19:04:28.171Z
- **Known versions:** 28
- **Latest version:** 0.1.36
- **Appeal under review:** No
- **Description:** Local runner for Agent Board — signs in with your own Supabase account (no shared secrets) and drives Claude Code against repos under your local repos root.
- **Maintainers:** paulaolileal
- **Runtime engines:** node: \>=18
- **Artifact files:** 4
- **Artifact unpacked size:** 413,113 bytes
- **Artifact signatures:** 2
- **Attestations:** No

## References
- [HTML security report](<https://firewall.lpm.dev/npm/agent-board-runner/v/0.1.34>)
