Enables agents to inspect PDF, Microsoft Office, and Apple iWork documents without rendering them, providing page/slide counts, metadata, security signals, structure, and integrity as deterministic JSON via typed tools and batch operations.
Protects AI agents from prompt injection attacks, jailbreak attempts, and common web vulnerabilities by screening untrusted input through semantic LLM analysis and static pattern matching.
Protects AI agents from threats like prompt injection, jailbreaks, and SQL injection through a multi-layer scanning pipeline. It also enables PII redaction and rehydration to ensure data privacy during LLM interactions.
A data-loss-prevention (DLP) layer for AI agents that intercepts document reads, scans for sensitive data, and redacts or blocks it before it reaches the model, with audit logging.
