Stop input Substrings
The StopInputSubstring detector checks and filters out banned substrings from input text prompt.
Vulnerability
Usage
Default dictionary includes common malware requests, eicar_signature
, gtube_signature
, gtphish_signature
and more.
Configuration
from guardrail.firewall.input_detectors import StopInputSubstrings
substrings = ["Project Apollo", "Project Chiron", "Patent #3728", "Apollo", "Chiron", "Jailbreak"]
firewall = Firewall()
input_detectors = [StopInputSubstrings(substrings=substrings)]
sanitized_prompt, valid_results, risk_score = firewall.scan_input(prompt, input_detectors)
Here's what the option is for:
substrings
(List[str]): user-provided substrings in addition to default patterns.- `case_sensitive``: bool = False,