Skip to main content

A Guardrails validator that scores prompts for injection attempts via a secondary LLM.

Project description

guardrails-ai-prompt-injection-detector

A Guardrails validator that scores prompts for injection attempts via a secondary LLM.

Installation

pip install guardrails-ai-prompt-injection-detector

This validator ships local models. After installing, run the post-install step to download them:

python -m guardrails_ai.prompt_injection_detector.post_install

Usage

from guardrails import Guard
from guardrails_ai.prompt_injection_detector import PromptInjectionDetector

guard = Guard().use(PromptInjectionDetector)

License

MIT — © Guardrails AI.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

File details

Details for the file guardrails_ai_prompt_injection_detector-0.0.2.tar.gz.

File metadata

File hashes

Hashes for guardrails_ai_prompt_injection_detector-0.0.2.tar.gz
Algorithm Hash digest
SHA256 93b7b99b4a1b2d56813b2efb9c998b3b53ddc132ed1b3eda1a110f78ba0a2a7a
MD5 47580837c4f565ee6fbd48a4c7dda29c
BLAKE2b-256 1075762e2e872c83b8d5ba9b7ee8fafa99dd2a7a2096e8187a2a1049d5153e05

See more details on using hashes here.

File details

Details for the file guardrails_ai_prompt_injection_detector-0.0.2-py3-none-any.whl.

File metadata

File hashes

Hashes for guardrails_ai_prompt_injection_detector-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 ed30585c1542d171c46e52c499ffa1c1675f37679e04b3576958de7d4a784f01
MD5 bf194216cdf686fcf40aaf4d3b215c61
BLAKE2b-256 cf14777b1c3262287c9cfa1f91022cc0cc021043bdf2afb5434e768dd53df0bf

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page