Skip to content

Add ClawGuard Shield — multi-language AI agent security scanner with EU AI Act mapping #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
joergmichno wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add ClawGuard Shield — multi-language AI agent security scanner with EU AI Act mapping #1

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
58 changes: 45 additions & 13 deletions security/tools.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,21 +67,53 @@ Invariant Guardrails provides a layer of protection against prompt injection and
- Offers policy-based controls for LLM interactions
- Integrates with existing security workflows


### ClawGuard Shield

ClawGuard Shield is a multi-language AI agent security scanner that detects prompt injection, tool poisoning, data exfiltration, and 189 attack patterns across 15 languages with zero LLM dependency. Includes EU AI Act compliance mapping.

**Key Features:**
- Detects prompt injection, tool poisoning, data exfiltration, SSRF, jailbreaks, and social engineering
- 189 detection patterns across 15 languages (EN, DE, FR, ES, IT, NL, PL, AR, HI, ID, ...)
- Zero LLM dependency — pure regex-based, under 10ms scan time
- EU AI Act risk category mapping (unique feature)
- OWASP LLM Top 10 + Agentic Top 10: 100% coverage
- F1 Score: 97.4% on benchmark suite
- Available as Python library, npm package, MCP server, and REST API

**Usage:**
```bash
# Python
pip install clawguard
clawguard scan "ignore previous instructions"

# MCP Server
npx clawguard-mcp

# API
curl -X POST https://prompttools.co/api/v1/scan -H "X-API-Key: YOUR_KEY" -d '{"text": "your input here"}'
```

**Access:**
- GitHub: [ClawGuard](https://github.com/joergmichno/clawguard)
- API Docs: [prompttools.co/api/docs](https://prompttools.co/api/docs)
- MCP Server: [Glama](https://glama.ai/mcp/servers/clawguard-mcp)

## <Icon icon="table" iconType="solid" /> Security Tools Comparison

| Feature | MCP-Scan | MCPScan.ai | Semgrep MCP | Invariant Guardrails |
|---------|----------|------------|-------------|----------------------|
| **Provider** | Invariant Labs | mcpscan.ai | Semgrep | Invariant Labs |
| **Primary Focus** | CLI-based MCP server security scanning | Web-based MCP vulnerability scanning | Code vulnerability scanning | LLM interaction security |
| **Installation/Access** | `uvx mcp-scan@latest` | Web service | `uvx semgrep-mcp` | API integration |
| **Detects Prompt Injection** | ✅ | ✅ | ❌ | ✅ |
| **Detects Tool Poisoning** | ✅ | ✅ | ❌ | ✅ |
| **Code Vulnerability Scanning** | ❌ | ✅ | ✅ | ❌ |
| **Tool Description Inspection** | ✅ | ✅ | ❌ | ❌ |
| **Cross-Origin Protection** | ✅ | ✅ | ❌ | ✅ |
| **Continuous Monitoring** | ❌ | ✅ (Enterprise) | ❌ | ✅ |
| **Knowledge Base** | ❌ | ✅ | ❌ | ❌ |
| **License** | Apache-2.0 | Commercial | MIT | Commercial |
| Feature | MCP-Scan | MCPScan.ai | Semgrep MCP | Invariant Guardrails | ClawGuard Shield |
|---------|----------|------------|-------------|----------------------|------------------|
| **Provider** | Invariant Labs | mcpscan.ai | Semgrep | Invariant Labs | joergmichno |
| **Primary Focus** | CLI-based MCP server security scanning | Web-based MCP vulnerability scanning | Code vulnerability scanning | LLM interaction security | Multi-language pattern-based security scanning |
| **Installation/Access** | `uvx mcp-scan@latest` | Web service | `uvx semgrep-mcp` | API integration | `pip install clawguard` / API / MCP |
| **Detects Prompt Injection** | ✅ | ✅ | ❌ | ✅ | ✅ |
| **Detects Tool Poisoning** | ✅ | ✅ | ❌ | ✅ | ✅ |
| **Code Vulnerability Scanning** | ❌ | ✅ | ✅ | ❌ | ❌ |
| **Tool Description Inspection** | ✅ | ✅ | ❌ | ❌ | ✅ |
| **Cross-Origin Protection** | ✅ | ✅ | ❌ | ✅ | ✅ |
| **Continuous Monitoring** | ❌ | ✅ (Enterprise) | ❌ | ✅ | ❌ |
| **Knowledge Base** | ❌ | ✅ | ❌ | ❌ | ❌ |
| **License** | Apache-2.0 | Commercial | MIT | Commercial | MIT |

## <Icon icon="shield-check" iconType="solid" /> Implementation Best Practices

Expand Down