---
canonical: "https://firewall.lpm.dev/npm/agent-board-runner/v/0.1.22"
markdown: "https://firewall.lpm.dev/npm/agent-board-runner/v/0.1.22.md"
package: "agent-board-runner"
report_status: "published"
title: "agent-board-runner@0.1.22 npm security report"
verdict: "suspicious"
version: "0.1.22"
---

# agent-board-runner@0.1.22 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:** 0.1.22
- **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 purpose is to run Claude Code on registered repositories, but sessions automatically trust the repository, approve its declared MCP servers, and skip Claude's permission checks. That creates a substantial agent capability risk, though the behavior is tied to the runner's stated automation purpose and is not evidence of credential theft or unrelated malicious activity.

## Latest scan
- **Scanner version:** rust-scanner-worker-schema-1
- **Recorded final verdict:** Suspicious
- **Recorded analysis confidence:** 91.0%
- **Started:** 2026-11-10T23:09:50.698Z
- **Finished:** 2026-11-10T23:10:27.174Z
- **Download time:** 520 ms
- **Static scan time:** 822 ms
- **AI review time:** 35133 ms
- **Total time:** 36476 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:** Automatically weakens Claude Code's safety controls for registered repositories by accepting trust and MCP approvals and running with permission checks skipped.

- **Trigger:** When an Agent Board task or workflow starts a Claude Code session for a registered repository.

- **Impact:** Repository-provided MCP servers and task instructions can run without normal Claude Code permission prompts, enabling actions the user may not have individually reviewed.

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

- **Review source:** ai\_review

- **Reviewed:** 2026-11-10T23:10:27.174Z

### AI review details

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

- **Mechanism:** Writes trust and enabled MCP server approvals for the repository into ~/.claude.json, then launches Claude Code with --dangerously-skip-permissions.

- **Rationale:** The package's purpose is to run Claude Code on registered repositories, but sessions automatically trust the repository, approve its declared MCP servers, and skip Claude's permission checks. That creates a substantial agent capability risk, though the behavior is tied to the runner's stated automation purpose and is not evidence of credential theft or unrelated malicious activity.

- **Files touched:** ~/.claude.json

- **Network endpoints:** https://supabase.lealtek.com

### Review decision

- **Verdict:** Suspicious

- **Confidence:** 91.0%

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

- **Intent class:** Dangerous Capability

- **False-positive risk:** Medium

- **Evidence for warning:** The package is a local runner intended to drive Claude Code against the user's registered repositories., When it launches Claude Code, it passes --dangerously-skip-permissions., Before launching, it marks the repository trusted and automatically approves MCP servers listed in that repository's .mcp.json in the user's ~/.claude.json., The trust and MCP approval changes are triggered by agent session startup, including workflow shell startup.

- **Evidence against:** The package's stated purpose is to run Claude Code against repositories selected by the user., The approval writes are scoped to registered repository paths and that repository's declared MCP servers., Network access is directed to the configured Agent Board Supabase service; no unrelated credential collector was identified.

## Affected versions and remediation

This report applies to agent-board-runner@0.1.22.

- Review the evidence and your use of agent-board-runner@0.1.22 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@0.1.22/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@0.1.22/dist/index.js>)

Package source references shell execution.

Public source snippet (untrusted):

```javascript
L344: import { spawn } from "node-pty";
L345: var SHELL_COMMAND = process.platform === "win32" ? process.env.COMSPEC ?? "cmd.exe" : process.env.SHELL ?? "bash";
L346: 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@0.1.22/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
L3647: // src/cloudflared.ts
L3648: import { spawn as spawn4 } from "node:child_process";
L3649: import { accessSync, constants } from "node:fs";
...
L3656: var BINARY_NAME = IS_WINDOWS2 ? "cloudflared.exe" : "cloudflared";
L3657: var CLOUDFLARED_INSTALL_DOCS_URL = "https://developers.cloudflare.com/cloudflare-one/connections/connect-networks/downloads/";
L3658: function wellKnownDirectories() {
...
L3661: const candidates = [
L3662: process.env.ProgramFiles && join13(process.env.ProgramFiles, "cloudflared"),
L3663: 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@0.1.22/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";
...
L240: };
L241: var useColor = process.stdout.isTTY;
L242: function paint(text, ...codes) {
...
L310: for (const socket of handle.sockets) {
L311: if (socket.readyState === socket.OPEN) socket.send(data);
L312: }
```

### 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:** 0.1.22
- **Version published:** 2026-11-10T23:06:20.950Z
- **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:** 405,939 bytes
- **Artifact signatures:** 2
- **Attestations:** No

## References
- [HTML security report](<https://firewall.lpm.dev/npm/agent-board-runner/v/0.1.22>)
