---
canonical: "https://firewall.lpm.dev/npm/openvisio-agent/v/0.3.1"
markdown: "https://firewall.lpm.dev/npm/openvisio-agent/v/0.3.1.md"
package: "openvisio-agent"
report_status: "published"
title: "openvisio-agent@0.3.1 npm security report"
verdict: "suspicious"
version: "0.3.1"
---

# openvisio-agent@0.3.1 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:** 0.3.1
- **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 has a real, user-invoked AI-agent configuration and persistence capability, so it warrants a warning. Static inspection found no automatic install-time execution or concrete malicious behavior.

## Latest scan
- **Scanner version:** rust-scanner-worker-schema-1
- **Recorded final verdict:** Suspicious
- **Recorded analysis confidence:** 87.0%
- **Started:** 2026-09-28T03:23:53.558Z
- **Finished:** 2026-09-28T03:26:55.999Z
- **Download time:** 510 ms
- **Static scan time:** 101 ms
- **AI review time:** 181829 ms
- **Total time:** 182441 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 explicit connect command changes the user's Claude MCP configuration. The explicit watch install option creates a persistent watcher and may globally install the package.

- **Trigger:** A user runs connect or watch with the install flag.

- **Impact:** These user-invoked actions can grant an OpenVisio MCP server agent access and persist an autonomy watcher; no automatic attack was established.

- **Evidence paths:** bin/cli.mjs, src/lib.mjs, src/watch.mjs

- **Review source:** ai\_review

- **Reviewed:** 2026-09-28T03:26:55.999Z

### AI review details

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

- **Mechanism:** The CLI invokes Claude MCP commands at user scope and the watcher invokes package installation when the binary is missing.

- **Rationale:** The package has a real, user-invoked AI-agent configuration and persistence capability, so it warrants a warning. Static inspection found no automatic install-time execution or concrete malicious behavior.

- **Files touched:** bin/cli.mjs, src/lib.mjs, src/watch.mjs

- **Network endpoints:** /api/agent/setup/exchange

### Review decision

- **Verdict:** Suspicious

- **Confidence:** 87.0%

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

- **Intent class:** Dangerous Capability

- **False-positive risk:** Low

- **Evidence for warning:** The manifest exposes a CLI entrypoint and contains no install lifecycle hook., The connect command removes and adds a user-scope Claude MCP server., Credential exchange sends the supplied setup token only to the caller-supplied host's setup path., Background service installation is gated by the explicit install flag., The service installer can globally install this same package when its binary is absent.

- **Evidence against:** No automatic npm lifecycle hook was found., No hidden endpoint, credential harvesting, or remote code evaluation was found in the inspected entrypoints.

## Affected versions and remediation

This report applies to openvisio-agent@0.3.1.

- Review the evidence and your use of openvisio-agent@0.3.1 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. High: Child Process
- **Category:** Source
- **Confidence:** 85.0%
- **Path:** bin/cli.mjs
- **Public source:** [View source](<https://unpkg.com/openvisio-agent@0.3.1/bin/cli.mjs>)

Package source references child process execution.

Public source snippet (untrusted):

```javascript
L11: 
L12: import { spawnSync } from 'node:child_process'
L13: import { mkdirSync, readFileSync, writeFileSync } from 'node:fs'
```

### 2. High: Shell
- **Category:** Source
- **Confidence:** 85.0%
- **Path:** src/lib.mjs
- **Public source:** [View source](<https://unpkg.com/openvisio-agent@0.3.1/src/lib.mjs>)

Package source references shell execution.

Public source snippet (untrusted):

```javascript
L38: export function onPath(cmd) {
L39: const r = spawnSync(IS_WIN ? `where ${cmd}` : `command -v ${cmd}`, { shell: true, encoding: 'utf8' })
L40: if (r.status !== 0) return null
```

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

Package source references network APIs.

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

Package source references environment variables.

### 5. Medium: Install Persistence
- **Category:** Source
- **Confidence:** 75.0%
- **Path:** src/watch.mjs
- **Public source:** [View source](<https://unpkg.com/openvisio-agent@0.3.1/src/watch.mjs>)

Source writes installer persistence such as shell profile or service configuration.

Public source snippet (untrusted):

```javascript
L6: 
L7: import { spawn, spawnSync } from 'node:child_process'
L8: import { writeFileSync, mkdirSync } from 'node:fs'
...
L11: import { OV_DIR, readConfig, onPath, fail, ok, info, slugify, stripSlash, chmodSafe } from './lib.mjs'
L12: import { connectAgentWs, assertWebSocket } from './ws.mjs'
L13: 
...
L19: const CODE_TOOLS = ['Read', 'Grep', 'Glob', 'Edit', 'Write', 'MultiEdit', 'TodoWrite', 'Bash', 'mcp__openvisio-team__*']
L20: const DENY_TOOLS = ['Bash(git push:*)', 'Bash(git reset --hard:*)', 'Bash(git clean:*)', 'Bash(rm:*)', 'Bash(sudo:*)', 'Bash(chmod:*)', 'Bash(curl:*)', 'Bash(wget:*)', 'Bash(npm pu...
L21: 
...
L32: const mcpConfig = String(flags['mcp-config'] || (saved && saved.mcpConfig) || '')
L33: const workdir = flags.workdir === true ? process.cwd() : (flags.workdir ? Strin
```

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

Package source references filesystem APIs.

### 7. High: Command Output Exfiltration
- **Category:** Source
- **Confidence:** 82.0%
- **Path:** src/lib.mjs
- **Public source:** [View source](<https://unpkg.com/openvisio-agent@0.3.1/src/lib.mjs>)

Source combines command execution, command-output handling, and outbound requests; review data flow before blocking.

Public source snippet (untrusted):

```javascript
L38: export function onPath(cmd) {
L39: const r = spawnSync(IS_WIN ? `where ${cmd}` : `command -v ${cmd}`, { shell: true, encoding: 'utf8' })
L40: if (r.status !== 0) return null
L41: return (r.stdout || '').trim().split(/\r?\n/)[0] || cmd
L42: }
...
L51: try {
L52: res = await fetch(url, { method: 'POST', headers: { 'content-type': 'application/json' }, body: JSON.stringify({ token }) })
L53: } catch (e) {
```

### 8. High: Sandbox Evasion Gated Capability
- **Category:** Source
- **Confidence:** 84.0%
- **Path:** src/watch.mjs
- **Public source:** [View source](<https://unpkg.com/openvisio-agent@0.3.1/src/watch.mjs>)

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

Public source snippet (untrusted):

```javascript
L6: 
L7: import { spawn, spawnSync } from 'node:child_process'
L8: import { writeFileSync, mkdirSync } from 'node:fs'
...
L11: import { OV_DIR, readConfig, onPath, fail, ok, info, slugify, stripSlash, chmodSafe } from './lib.mjs'
L12: import { connectAgentWs, assertWebSocket } from './ws.mjs'
L13: 
...
L19: const CODE_TOOLS = ['Read', 'Grep', 'Glob', 'Edit', 'Write', 'MultiEdit', 'TodoWrite', 'Bash', 'mcp__openvisio-team__*']
L20: const DENY_TOOLS = ['Bash(git push:*)', 'Bash(git reset --hard:*)', 'Bash(git clean:*)', 'Bash(rm:*)', 'Bash(sudo:*)', 'Bash(chmod:*)', 'Bash(curl:*)', 'Bash(wget:*)', 'Bash(npm pu...
L21: 
...
L32: const mcpConfig = String(flags['mcp-config'] || (saved && saved.mcpConfig) || '')
L33: const workdir = flags.workdir === true ? process.cwd() : (flags.workdir ? Strin
```

### 9. High: Trigger Reachable Command Output Exfiltration
- **Category:** Source
- **Confidence:** 94.0%
- **Path:** src/lib.mjs
- **Public source:** [View source](<https://unpkg.com/openvisio-agent@0.3.1/src/lib.mjs>)

A manifest entrypoint or package-local install chain reaches command-output exfiltration behavior.

Public source snippet (untrusted):

```javascript
Trigger-reachable command-output exfiltration chain: manifest.bin -> bin/cli.mjs -> src/lib.mjs
L38: export function onPath(cmd) {
L39: const r = spawnSync(IS_WIN ? `where ${cmd}` : `command -v ${cmd}`, { shell: true, encoding: 'utf8' })
L40: if (r.status !== 0) return null
L41: return (r.stdout || '').trim().split(/\r?\n/)[0] || cmd
L42: }
...
L51: try {
L52: res = await fetch(url, { method: 'POST', headers: { 'content-type': 'application/json' }, body: JSON.stringify({ token }) })
L53: } catch (e) {
```

### 10. High: Trigger Reachable Persistence
- **Category:** Source
- **Confidence:** 94.0%
- **Path:** src/watch.mjs
- **Public source:** [View source](<https://unpkg.com/openvisio-agent@0.3.1/src/watch.mjs>)

A manifest entrypoint or package-local install chain reaches persistence behavior.

Public source snippet (untrusted):

```javascript
Trigger-reachable persistence chain: manifest.bin -> bin/cli.mjs -> src/watch.mjs
L6: 
L7: import { spawn, spawnSync } from 'node:child_process'
L8: import { writeFileSync, mkdirSync } from 'node:fs'
...
L11: import { OV_DIR, readConfig, onPath, fail, ok, info, slugify, stripSlash, chmodSafe } from './lib.mjs'
L12: import { connectAgentWs, assertWebSocket } from './ws.mjs'
L13: 
...
L19: const CODE_TOOLS = ['Read', 'Grep', 'Glob', 'Edit', 'Write', 'MultiEdit', 'TodoWrite', 'Bash', 'mcp__openvisio-team__*']
L20: const DENY_TOOLS = ['Bash(git push:*)', 'Bash(git reset --hard:*)', 'Bash(git clean:*)', 'Bash(rm:*)', 'Bash(sudo:*)', 'Bash(chmod:*)', 'Bash(curl:*)', 'Bash(wget:*)', 'Bash(npm pu...
L21: 
...
L32: const mcpConfig = String(flags['mcp-config'] || (saved && saved.mcpConfig) || '')
L3
```

### 11. High: Runtime Package Install
- **Category:** Source
- **Confidence:** 86.0%
- **Path:** src/lib.mjs
- **Public source:** [View source](<https://unpkg.com/openvisio-agent@0.3.1/src/lib.mjs>)

Package source invokes a package manager install command at runtime.

Public source snippet (untrusted):

```javascript
L68: info('Claude Code not found on PATH — installing @anthropic-ai/claude-code globally…')
L69: spawnSync('npm', ['i', '-g', '@anthropic-ai/claude-code'], { stdio: 'inherit', shell: IS_WIN })
L70: claude = onPath('claude')
L71: if (!claude) fail('Claude Code still isn\'t on PATH after install.\n  Install it (npm i -g @anthropic-ai/claude-code), open a new terminal, and re-run.')
L72: return claude
```

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

Package source contains high-entropy string patterns.

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

Package source contains URL literals.

### 14. Medium: Structural Risk Force Deep Review
- **Category:** Artifact Inventory
- **Confidence:** 100.0%

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

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

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

## Package metadata
- **Package:** openvisio-agent
- **Ecosystem:** npm
- **Version:** 0.3.1
- **License:** MIT
- **Version published:** 2026-08-24T22:32:11.329Z
- **Package first seen:** 2026-08-25T23:45:41.667Z
- **Package last seen:** 2026-11-16T15:27:19.479Z
- **Known versions:** 72
- **Latest version:** 0.30.7
- **Appeal under review:** No
- **Description:** Connect your coding agent (Claude Code) to an OpenVisio team — MCP tools + optional autonomy — in one command. No shell scripts.
- **Maintainers:** brimai
- **Keywords:** openvisio, mcp, claude, claude-code, agent, autonomy
- **Runtime engines:** node: \>=18
- **Artifact files:** 6
- **Artifact unpacked size:** 40,582 bytes
- **Artifact signatures:** 1
- **Attestations:** No

## References
- [HTML security report](<https://firewall.lpm.dev/npm/openvisio-agent/v/0.3.1>)
- [Repository](<https://github.com/syntaxPriest/OpenVisio>)
- [Homepage](<https://github.com/syntaxPriest/OpenVisio#readme>)
- [Issues](<https://github.com/syntaxPriest/OpenVisio/issues>)
