Meta

• License: MIT License (MIT License)
• Author: Sai Teja Erukude
• Tags ai , firewall , jailbreak , llm , pii , prompt , prompt-injection , rce , redaction , secrets , security , ssrf
• Requires: Python >=3.10
• Provides-Extra: all , anthropic , dev , openai

Classifiers

• Development Status
  • 4 - Beta
• Intended Audience
  • Developers
• License
  • OSI Approved :: MIT License
• Programming Language
  • Python :: 3
  • Python :: 3.10
  • Python :: 3.11
  • Python :: 3.12
• Topic
  • Security
  • Software Development :: Libraries :: Python Modules

promptsanitizer

Secrets firewall for AI pipelines.

promptsanitizer helps redact, block, and audit sensitive data before it reaches an LLM — and before risky model outputs leave your application.

Why this exists

AI systems often pass user input, retrieved documents, tool outputs, and model responses through LLMs. That text can contain API keys, credentials, PII, or prompt injection attempts.

What it checks

• API keys, tokens, passwords, private keys, and cloud credentials
• PII such as emails, phone numbers, SSNs, credit cards, and IP addresses
• Prompt injection and jailbreak-style instructions
• Risky code execution patterns
• Exfiltration indicators such as internal URLs, metadata endpoints, and webhook-style payloads

Install

pipinstallpromptsanitizer

Optional integrations:

pipinstall"promptsanitizer[openai]"
pipinstall"promptsanitizer[anthropic]"
pipinstall"promptsanitizer[all]"

Quick Start

frompromptsanitizerimport Firewall

fw = Firewall()

text = "My API key is sk-proj-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
safe_text = fw.clean(text)

print(safe_text)

My API key is [REDACTED:openai_key]

Core features

• Inbound prompt scanning
• Outbound response scanning
• Redaction, blocking, and audit-only modes
• Default, strict, audit, and custom policies
• CLI support
• OpenAI and Anthropic middleware wrappers
• Compliance-style findings and reports
• Custom detection patterns

Who should use this

• AI engineers
• ML platform teams
• Security engineers
• Researchers
• Teams building agents, RAG systems, copilots, and AI assistants

Examples

Detailed examples are kept in the examples/ folder to keep this README simple.

examples/
basic_clean.py
strict_policy.py
custom_policy.py
prompt_injection_detection.py
outbound_response_scan.py
compliance_report.py
openai_middleware.py
anthropic_middleware.py
cli_scan.sh
cli_report.sh

CLI

promptsanitizerscan"email: dev@example.com"

promptsanitizerclean"my key is sk-proj-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"

promptsanitizerreport--fileprompt.txt

Where it fits

Userinput
->promptsanitizer
->LLM/agent/RAGpipeline
->promptsanitizer
->user/logs/downstreamsystems

Limitations

promptsanitizer is a defensive scanning layer, not a complete security boundary. Use it alongside access controls, secret management, logging controls, tool isolation, and output validation.

Verified details

These details have been verified by PyPI

Maintainers

👁 Avatar for erukude from gravatar.com
erukude

Unverified details

These details have not been verified by PyPI

Project links

• Bug Tracker
• Changelog
• Homepage
• Repository

• Download URL: promptsanitizer-1.1.1.tar.gz
• Upload date: May 31, 2026
• Size: 17.4 kB
• Tags: Source
• Uploaded using Trusted Publishing? No
• Uploaded via: twine/6.2.0 CPython/3.13.7

Hashes for promptsanitizer-1.1.1.tar.gz

Algorithm	Hash digest
SHA256	1a84f692b6616e54f49b07f819cdd0aca46b57aac2faa6f542e39e6a2f73d314
MD5	060fdfd4c874bfd4ce3e7a534f1f62a3
BLAKE2b-256	1ed1485b3d36f241b120d9f41b8fbf24d36f2a9916130613702be130f0c3746f

See more details on using hashes here.

• Download URL: promptsanitizer-1.1.1-py3-none-any.whl
• Upload date: May 31, 2026
• Size: 18.1 kB
• Tags: Python 3
• Uploaded using Trusted Publishing? No
• Uploaded via: twine/6.2.0 CPython/3.13.7

Hashes for promptsanitizer-1.1.1-py3-none-any.whl

Algorithm	Hash digest
SHA256	6cde76bd90c501da5dc20a53b0867b079a89618f66062ef08202e2dbd793c68e
MD5	5f65fa7e83750f0dd81cf4b4bb642d5b
BLAKE2b-256	8a128daf7236704e43d2c319cf967ceb3804d372f4f8c669d5fc25f3ee927196

See more details on using hashes here.