Data Loss Prevention Python Packages

ferret-scan

Find and redact sensitive data before it leaks — a fast, offline CLI and Go library that detects PII, secrets, and credentials in files and streams, scores them with context-aware confidence, and redacts them format-preserving. Nothing leaves your host.

bedrock-guardrail-firewall

Stop unsafe AI traffic before it spreads with enterprise PII redaction, prompt-injection defense, grounding checks, tamper-evident auditing, and optional Amazon Bedrock plus Presidio controls in one Python file.

traceredact

Redact PII & secrets from LLM prompts, agent traces & tool-call args before they hit your logs. Content-based detection (not just key names), CI-gateable, zero data retained.

pyredactkit

Python CLI tool to redact and un-redact sensitive data from text files. 🔐📝

n0s1

Secret Scanner for Slack, Jira, Confluence, Asana, Wrike, Linear, Zendesk, GitHub, and GitLab

zugashield

7-layer AI agent security system — stop prompt injection, data exfiltration, and AI-specific attacks in under 15ms. Zero dependencies.

sharelint

Local privacy preflight for files, folders, and archives—catch secrets, PII, metadata, and hidden document content before sharing.

contextduty

Local-first prompt firewall — stop secrets & PII from reaching AI tools (IDE, git, AI-API proxy, MCP). Built on Microsoft Presidio.

strac-mcp-dlp

MCP server for Strac DLP — detect and redact PII, PHI, PCI and secrets before an AI agent sees them.

forcefield

ForceField Python SDK -- AI security in 3 lines of code. Prompt injection detection, PII redaction, security evals, tool governance. GitHub Action, pre-commit hook, Homebrew, VS Code extension.

privacyscrubber-mcp

Zero-Trust PII & secrets redaction MCP server for Cursor & Claude. Lightweight, zero-dependency Presidio alternative for Node.js / TypeScript.

nightfall

Python Data Loss Prevention (DLP) SDK - Nightfall Developer Platform

ztds

ZTDS.ai — Zero-Trust Data Sanitization (ZTDS) Open Specification, RFC v1.0, and Consortium

pii-lens

Highlight credit cards, emails, phone numbers, SSNs, and US bank numbers in logs and prompts before they hit an LLM.

molecare-privacy-gate

Keep sensitive prompts local: a 1,024-weight head on bge-m3 that catches health data, credentials and PII written as plain English, which regex and entity tools miss. A second gate for LLM routers and guardrails. Not a medical device.

langchain-forcefield

ForceField Python SDK -- AI security in 3 lines of code. Prompt injection detection, PII redaction, security evals, tool governance. GitHub Action, pre-commit hook, Homebrew, VS Code extension.

llm-securescan

A new package is designed to facilitate secure and structured user interactions with language models by analyzing and extracting specific information from user-provided text. It uses pattern matching

gitlab-watchman

Finding exposed secrets and personal data in GitLab

occludra

Self-hosted AI security proxy. Redact PII, block prompt injection, route to any LLM provider. OpenAI-compatible.

pleno-dlp

Verify by Default. Unified DLP scanner.

aisg

Self-hosted AI security proxy. Redact PII, block prompt injection, route to any LLM provider. OpenAI-compatible.

pleno-secret-scanner

Verify by Default. Unified DLP scanner.

txtferret

Identify and classify data in your text files with Python.

novisentinel

Scan LLM inputs and outputs for PII, prompt injection, secrets, and toxicity. Python SDK, FastAPI middleware, VS Code extension included.