Adversarial Prompt Attacks

Name: Adversarial Prompt Attacks — synthetic Indian test data
Creator: Techtrapture Private Limited
License: https://datatrapture.com/terms

A library of malicious prompts (jailbreaks, injections, PII-extraction attempts) for testing whether an AI system correctly blocks bad requests.

Rows: 771
Region: India
Labeled PII: No
Fraud labels: No

What you can test with it

Test AI guardrail and red-team evaluation on India-shaped data rather than US-shaped placeholders.
Populate a lower environment, demo or training set without touching real customer data.

Fields

prompt_ref
category
attack_family
target
technique
obfuscation
language
severity
is_malicious
is_benign
expected_behavior
prompt_text
char_len
purpose
region_code

Is this data safe to use?

Yes. Every record is generated, never derived from or masked from real people, and every identifier is non-issuable by construction — correctly formatted, but failing checksum validation or using a reserved range so it can never match a real person or institution.