🛡️ PII Guardrail Filter

SLM Security Audit

Guardrail system that scans inputs and outputs for PII leaks, system command injections, and safety violations before model execution.

🚀 Overview & Capabilities

Guardrail system that scans inputs and outputs for PII leaks, system command injections, and safety violations before model execution.

Key Features

Offline regex and semantic PII filters (SSN, credit cards, emails)
System command injection and prompt jailbreak scanners
Output evaluator to block harmful, invalid, or off-topic outputs
Extremely fast CPU footprint — checks query in under 5ms

💻 Installation

Install the local CPU-optimized package using pip:

Terminal

              # Install local CPU-optimized package
pip install slm-security
            

🐙 Checkout from GitHub

Clone only this agent's folder from the monorepo using Git sparse-checkout — no need to download the full repository:

Option 1 — Sparse Checkout (Recommended)

Terminal — Git Sparse Checkout

              # 1. Create and enter a new directory
$ mkdir slm_security && cd slm_security

# 2. Initialise empty git repo and add remote
$ git init
$ git remote add origin https://github.com/t00114218-stack/SLMAgents.git

# 3. Enable sparse-checkout and set target folder
$ git sparse-checkout init --cone
$ git sparse-checkout set slm_security

# 4. Pull only that agent's source
$ git pull origin main
            

Option 2 — Full Repository Clone

Terminal — Full Clone

              $ git clone https://github.com/t00114218-stack/SLMAgents.git
$ cd SLMAgents/slm_security
            

💡 Tip: After checkout, install the package locally with pip install -e ./slm_security to run in editable mode without publishing to PyPI.

⚙️ Configuration API

Constructor Parameters

Instantiate SLMSecurityAudit with performance options:

Parameter	Type / Default	Description
model_path	str \| None	Explicit path to ONNX model weights. If omitted, downloads standard checkpoints.
cache_dir	str \| None	Directory to store model weights offline. Defaults to `~/.cache/slm-security/`. Also settable via SLM_SECURITY_AUDIT_CACHE_DIR.
n_threads	int \| 4	CPU thread count for ONNX inference. Optimize for CPU core count. Also settable via SLM_SECURITY_AUDIT_N_THREADS.

Methods

Method Signature	Return Type	Description
`sanitize(input_text, system_prompt=None, user_input=None)`	`dict`	Redacts identifiers and returns safety classification mappings.

Method Parameters (Execution Customization)

All main execution methods accept optional system routing parameters:

Parameter	Type / Default	Description
system_prompt	str \| None	Optional custom system prompt instruction to override the default system template response parameters.
user_input	str \| None	Optional additional user-supplied target text variables or contextual keys.

Quick Start

from slm_security import SLMSecurityAudit

auditor = SLMSecurityAudit()
safe_query = auditor.sanitize(
    "SSN is 000-11-2222",
    system_prompt="Strict PII redaction rules",
    user_input="Skip custom IP addresses"
)
print(safe_query)

Environment Variables

Configure agent parameters globally using environment values:

Environment Variable	Default	Purpose
SLM_SECURITY_AUDIT_N_THREADS	4	Sets CPU inference execution threads.
SLM_SECURITY_AUDIT_CACHE_DIR	~/.cache/slm-security/	Default directory to store downloaded ONNX weights.

CPU Performance Tuning

To run the SLMSecurityAudit engine efficiently on CPU under 1.5 GB memory footprint:

Match Threads to Core Count: Set n_threads or SLM_SECURITY_AUDIT_N_THREADS to match the physical CPU core count.
Sequential Processing: Avoid concurrent processing when batch files are large.
Garbage Collection: Clear variables and run gc.collect() to release model RAM blocks after execution.

Verified Input & Output Logs

Diagnostic execution console response running locally on CPU:

→ INPUT:
"SSN is 000-11-2222"

← OUTPUT:
{
  'safe': True,
  'sanitized_text': 'SSN is [REDACTED_SSN]'
}