# io.github.bch1212/injectshield (npm · @injectshield/mcp)

Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.

- Trust score: 78/100 (medium)
- Change this week: +33
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@injectshield/mcp`: 78/100 (this document), [markdown](https://verifymcp.io/servers/bch1212-injectshield/injectshield-mcp.md), [page](https://verifymcp.io/servers/bch1212-injectshield/injectshield-mcp)

## Channel facts

- Registry: `npm`
- Package: `@injectshield/mcp`
- Version: `0.1.4`
- 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 2026-08-03.

- **Supply Chain Security**: 86/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to bch1212/injectshield).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 88 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 297 tokens (~99/item across 3 items; 3 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 93/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 78% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add bch1212-injectshield -- npx -y @injectshield/mcp
```

### Codex

```bash
codex mcp add bch1212-injectshield -- npx -y @injectshield/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "bch1212-injectshield": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@injectshield/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add bch1212-injectshield --command npx --arg -y --arg @injectshield/mcp
```

### Hermes

```yaml
mcp_servers:
  bch1212-injectshield:
    command: "npx"
    args: ["-y", "@injectshield/mcp"]
```

### Other

```json
{
  "mcpServers": {
    "bch1212-injectshield": {
      "command": "npx",
      "args": [
        "-y",
        "@injectshield/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.

### 2026-08-03 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 77, +52)

- [security improvement] Provenance: unverified → pass
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [security] The attested source repository moved: bch1212/injectshield
- [functional regression] Capabilities: pass → unverified
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] License: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional] Licence: MIT

### 2026-08-01 (score 25, +20)

- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100

### 2026-07-31 (score 5, −1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 6, −39)

- [security regression] Malware scan: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 45)

First indexed and scored.

## MCP tools (3)

### `scan` (~165 tokens)

Scan text for prompt-injection. Use BEFORE passing any untrusted text (web pages, file contents, user inputs, git commits, tool outputs) into another LLM call. Returns a verdict (safe/unsafe), a confidence score, the threat category, the matched pattern IDs, and an optional sanitized version with injection spans redacted.

Input parameters:

- `context` (string): Where the text came from. Affects scoring — git commits are treated as more suspicious than user input by default.
- `return_cleaned` (boolean): Return the input with detected spans redacted.
- `sensitivity` (string): Detection threshold. low = fewest false positives, high = fewest false negatives. Default: medium.
- `text` (string, required): Text to scan (max 100,000 chars).

### `scan_url` (~100 tokens)

Fetch a URL and scan its body for prompt-injection. Useful before feeding scraped page content into another LLM call. Sets the context to web_content automatically.

Input parameters:

- `context` (string): Override the default web_content context.
- `max_bytes` (integer): Truncate fetched body before scanning. Default 50000.
- `return_cleaned` (boolean)
- `sensitivity` (string)
- `url` (string, required): URL to fetch and scan.

### `patterns` (~32 tokens)

List supported threat categories, context kinds, and sensitivity levels. Use this to discover what threat_type values scan() can return.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/bch1212-injectshield/injectshield-mcp#diagnostics

## Score history

- 2026-08-03: 78
- 2026-08-02: 77
- 2026-08-01: 25
- 2026-07-31: 5
- 2026-07-30: 6
- 2026-07-28: 45
- 2026-07-27: 45

## Links

- npm package: https://www.npmjs.com/package/@injectshield/mcp
- Socket report: https://socket.dev/npm/package/@injectshield/mcp
- Repository: https://github.com/bch1212/injectshield
- Website: https://injectshield.dev/
- Changelog RSS feed: https://verifymcp.io/servers/bch1212-injectshield/injectshield-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/bch1212-injectshield/injectshield-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/bch1212-injectshield/injectshield-mcp