Validate Agent

Screen untrusted text before it reaches your LLM. Catches obfuscation techniques including homoglyph substitution, zero-width character insertion, base64-encoded payloads, and multilingual attacks. Returns risk level, matched patterns, and cleaned text.

Find and redact personal data before logging, storing, or forwarding text. Detects SSNs, credit card numbers, emails, phone numbers, IP addresses, dates of birth, passport numbers, and IBANs. NER-powered when available, with regex fallback. Returns span locations and redacted text.

Remove XSS vectors from untrusted HTML without installing a sanitizer locally. Powered by nh3 (Rust). Strips script tags, event handlers, data URIs, and other injection vectors. Returns clean HTML plus threat metadata.

Validate SQL syntax and detect injection patterns before executing queries. Supports 30+ dialects via sqlglot including PostgreSQL, MySQL, BigQuery, Snowflake, and SQLite. Catches tautologies, UNION attacks, and stacked queries.

Validate and normalize emails, URLs, UUIDs, phone numbers, and IPv4 addresses. RFC-compliant checks with normalization output. Ideal for agents in sandboxed environments that cannot install validation libraries.

Validate any JSON data against a JSON Schema definition. Supports Draft 4, 6, 7, 2019-09, and 2020-12. Use to verify LLM-generated structured output matches expected format.

Validate up to 1,000 values in a single request. Mix types freely — emails, URLs, UUIDs, phones, IPv4 in one call. Returns per-item results with a summary. Cheaper per-item than individual calls.