# vibe-shield — security scanner for AI-generated code (npm · @vibefoundry/vibe-shield)

Scans AI-written code for leaked secrets, unguarded routes and missing RLS.

- Trust score: 74/100 (medium)
- Change this week: +5
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- npm · `@vibefoundry/vibe-shield`: 74/100 (this document), [markdown](https://verifymcp.io/servers/avivgerz-hue-vibe-shield/vibefoundry-vibe-shield.md), [page](https://verifymcp.io/servers/avivgerz-hue-vibe-shield/vibefoundry-vibe-shield)

## Channel facts

- Registry: `npm`
- Package: `@vibefoundry/vibe-shield`
- Version: `2.1.3`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 3 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 73/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 592 tokens (~197/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the vibe-shield — security scanner for AI-generated code MCP server?

vibe-shield — security scanner for AI-generated code runs locally as an npm package, launched with npx -y @vibefoundry/vibe-shield mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add avivgerz-hue-vibe-shield -- npx -y @vibefoundry/vibe-shield mcp
```

### Cursor

```json
{
  "mcpServers": {
    "avivgerz-hue-vibe-shield": {
      "command": "npx",
      "args": [
        "-y",
        "@vibefoundry/vibe-shield",
        "mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "avivgerz-hue-vibe-shield": {
      "command": "npx",
      "args": [
        "-y",
        "@vibefoundry/vibe-shield",
        "mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add avivgerz-hue-vibe-shield -- npx -y @vibefoundry/vibe-shield mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "avivgerz-hue-vibe-shield": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@vibefoundry/vibe-shield",
        "mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add avivgerz-hue-vibe-shield --command npx --arg -y --arg @vibefoundry/vibe-shield --arg mcp
```

### Hermes

```yaml
mcp_servers:
  avivgerz-hue-vibe-shield:
    command: "npx"
    args: ["-y", "@vibefoundry/vibe-shield", "mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "avivgerz-hue-vibe-shield": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@vibefoundry/vibe-shield",
        "mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add avivgerz-hue-vibe-shield -t stdio -c npx -a -y @vibefoundry/vibe-shield mcp
```

### Other

```json
{
  "mcpServers": {
    "avivgerz-hue-vibe-shield": {
      "command": "npx",
      "args": [
        "-y",
        "@vibefoundry/vibe-shield",
        "mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 73, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-11-17 (score 57, −15)

- [security regression] Malware scan: pass → unverified
- [functional] Package version: 2.1.2 → 2.1.3

### 2026-11-16 (score 72, +3)

- [functional improvement] Stability: unverified → 0.20

### 2026-11-11 (score 69, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-10 (score 54)

First indexed and scored.

## MCP tools (3)

### `vibe_shield_scan` (~250 tokens)

Scan a project for AI-introduced security bugs

Runs the 60-rule vibe-shield scanner over a project directory or a set of paths and returns the grade, score and every finding with its exact file, line, CWE and remediation steps. Call this after writing or modifying application code — API routes, server actions, database migrations, auth logic, environment variables, LLM calls or webhook handlers — and before reporting a task as complete. Also call it when the user asks for a security review or audit.

Input parameters:

- `includeDocs` (boolean): Include Markdown and documentation files.
- `includeTests` (boolean): Include test, spec and fixture files.
- `limit` (integer): Maximum findings to return in the text summary. Default 25, 0 for all.
- `paths` (array): Explicit files or directories to scan, instead of the whole project.
- `rules` (array): Restrict to these rule ids or prefixes, e.g. ["VSB-CLIENT-001"] or ["VSB-DB-*"].
- `severity` (string): Only return findings at or above this severity.
- `target` (string): Directory or file to scan. Relative paths resolve against the server working directory. Default: the working directory.

### `vibe_shield_audit_skills` (~162 tokens)

Audit agent skills and MCP configuration for poisoning

Audits .claude/skills, .cursor rules, .cursorrules, AGENTS.md, CLAUDE.md and MCP config files (mcp.json, .mcp.json) for agent-poisoning: hidden Unicode instructions, credential exfiltration commands, reads of .env or ~/.ssh, unpinned MCP servers, literal credentials and safety-override language. Call this whenever you add or modify an agent instruction file, a skill, a Cursor rule or an MCP server config.

Input parameters:

- `limit` (integer): Maximum findings to return. Default 25.
- `paths` (array): Specific agent files or directories to audit.
- `target` (string): Project root to audit. Default: the server working directory.

### `vibe_shield_explain_rule` (~105 tokens)

Explain a detection rule

Returns the full documentation for one rule id or slug: severity, confidence, CWE, why it is exploitable, the vulnerable code shape, the fixed code shape, ordered remediation steps and references. Use this when you need to understand a finding before fixing it, or when the user asks what a rule means.

Input parameters:

- `ruleId` (string, required): Rule id or slug, e.g. "VSB-CLIENT-001" or "public-env-secret-exposure".

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/avivgerz-hue-vibe-shield/vibefoundry-vibe-shield#diagnostics

## Score history

- 2026-11-21: 74
- 2026-11-20: 74
- 2026-11-19: 73
- 2026-11-18: 73
- 2026-11-17: 57
- 2026-11-16: 72
- 2026-11-15: 69
- 2026-11-14: 69
- 2026-11-13: 69
- 2026-11-12: 69
- 2026-11-11: 69
- 2026-11-10: 54

## Common questions

### What is the vibe-shield — security scanner for AI-generated code MCP server?

vibe-shield — security scanner for AI-generated code is an MCP server listed in the public MCP registry as io.github.avivgerz-hue/vibe-shield. Scans AI-written code for leaked secrets, unguarded routes and missing RLS. This page covers its npm package (@vibefoundry/vibe-shield).

### Is the vibe-shield — security scanner for AI-generated code MCP server safe to use?

vibe-shield — security scanner for AI-generated code scores 74 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the vibe-shield — security scanner for AI-generated code MCP server expose?

vibe-shield — security scanner for AI-generated code exposes 3 tools: vibe_shield_scan, vibe_shield_audit_skills, vibe_shield_explain_rule. Their descriptions and schemas cost roughly 517 tokens of context every time the server is loaded.

### Is the vibe-shield — security scanner for AI-generated code MCP server still maintained?

vibe-shield — security scanner for AI-generated code is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the vibe-shield — security scanner for AI-generated code MCP server under?

vibe-shield — security scanner for AI-generated code declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the vibe-shield — security scanner for AI-generated code MCP server?

VerifyMCP ran 16 checks on vibe-shield — security scanner for AI-generated code, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/@vibefoundry/vibe-shield
- Socket report: https://socket.dev/npm/package/@vibefoundry/vibe-shield
- Repository: https://github.com/avivgerz-hue/vibe-shield
- Changelog RSS feed: https://verifymcp.io/servers/avivgerz-hue-vibe-shield/vibefoundry-vibe-shield.xml
- Changelog JSON feed: https://verifymcp.io/servers/avivgerz-hue-vibe-shield/vibefoundry-vibe-shield/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/avivgerz-hue-vibe-shield/vibefoundry-vibe-shield.json
- HTML version of this page: https://verifymcp.io/servers/avivgerz-hue-vibe-shield/vibefoundry-vibe-shield
