PIIGuard: Mitigating PII Harvesting under Adversarial Sanitization

Browsing-enabled LLM assistants can fetch webpages and answer contact-seeking queries, creating a practical channel for scraping contact-style personally identifiable information PII from public pages. Many prior defenses are deployed at the model, service, or agent layer rather than at the webpa...

CVE-2025-30191

Malicious content from E-Mail can be used to perform a redressing attack. Users can be tricked to perform unintended actions or provide sensitive information to a third party which would enable further threats. Attribute values containing HTML fragments are now denied by the sanitization procedur...