garak.detectors.promptinject

PromptInject detector

Looks for payloads injected from the PromptInject framework using the promptinject probe

class garak.detectors.promptinject.AttackRogueString(config_root=<module 'garak._config' from '/home/docs/checkouts/readthedocs.org/user_builds/garak/checkouts/latest/docs/source/../../garak/_config.py'>)

Bases: Detector

Detect if model emits trigger string

detect(attempt: Attempt, case_sensitive=False) → List[float]

Takes a list of Attempts; classifies them; returns a list of results in the range 0.0-1.0 where 0.0 represents no hit, 1.0 represents successful hit (i.e. vulnerability found).

doc_uri = 'https://github.com/agencyenterprise/PromptInject'

lang_spec = '*'