Input Sanitisation
This skill cleans user inputs to prevent vulnerabilities like injection attacks, ensuring safer and more reliable AI interactions.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add input-sanitisation npx -- -y @trustedskills/input-sanitisation
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"input-sanitisation": {
"command": "npx",
"args": [
"-y",
"@trustedskills/input-sanitisation"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill sanitizes user input to prevent malicious code injection and ensure data integrity. It removes or escapes potentially harmful characters, making applications more secure against attacks like cross-site scripting (XSS) and SQL injection. The skill aims to produce safe and reliable data for further processing.
When to use it
- Processing User Form Data: Before storing user input from web forms in a database.
- Handling API Requests: Sanitizing data received from external APIs before using it within your application.
- Generating Dynamic Content: Cleaning up user-provided content for display on websites or in applications.
- Building Chatbots: Ensuring chatbot inputs are safe and free of potentially harmful commands.
Key capabilities
- Removes or escapes malicious characters.
- Prevents XSS attacks.
- Mitigates SQL injection vulnerabilities.
- Ensures data integrity.
Example prompts
- "Sanitize this user input:
<script>alert('XSS')</script>" - "Clean the following string for safe display:
'; DROP TABLE users; --" - “Remove any HTML tags from this text.”
Tips & gotchas
The effectiveness of sanitization depends on the specific types of attacks you're trying to prevent. Consider carefully which characters need to be removed or escaped based on your application’s context and data usage.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.