Secure AI and comply with GDPR and the AI Act
Guardrails, attack tests and AI Act files for reliable, compliant AI.
- [1x2ywyz] Guardrail: mask API keys and passwords | guardrail | en | MIT | https://contextetech.com/en/guardrails/mask-secrets-api-keys-1x2ywyz - [hx10ow] AI context to anonymize personal data in English text | context | en | CC-BY-4.0 | https://contextetech.com/en/contexts/anonymize-english-text-hx10ow - [145862m] Guardrail: mask U.S. personal data (SSN, phone, card) | guardrail | en | MIT | https://contextetech.com/en/guardrails/mask-us-personal-data-145862m - [uka0js] Red teaming: 12 attacks on a customer service chatbot | redteam | en | MIT | https://contextetech.com/en/red-teaming/us-customer-service-chatbot-attacks-uka0js - [4o5cbb] Red teaming: 10 tests on a U.S. HR assistant | redteam | en | MIT | https://contextetech.com/en/red-teaming/us-hr-assistant-tests-4o5cbb
Guardrail: mask API keys and passwords
Guardrail that masks API keys, tokens, passwords, private keys and connection strings before a text, file or export is sent to an AI. Rules, 14 test cases…
AI context to anonymize personal data in English text
AI context that replaces personal data in English text (names, emails, phones, addresses, SSNs, medical record numbers) with tags before sharing it.
Guardrail: mask U.S. personal data (SSN, phone, card)
Guardrail that masks U.S. personal data in AI assistant replies: SSNs, +1 phone numbers, personal emails and card numbers. Rules, 12 tests, code.
Red teaming: 12 attacks on a customer service chatbot
12 attacks to replay on a U.S. e-commerce support chatbot: impersonation, data leaks, prompt injection, unauthorized refunds. Expected reply for each.
Red teaming: 10 tests on a U.S. HR assistant
10 tests for an internal HR assistant in the U.S.: employee data, hiring discrimination (EEOC), impersonation, injection, and 2 legitimate questions.
What does securing AI mean?
Securing AI means limiting what it can say or do: block personal data, resist prompt injection, stay within scope. It also means proving it is reliable and compliant, with GDPR and the AI Act, through attack tests and documentation.