A2A Indirect Prompt-Injection & Jailbreak Firewall

Use this endpoint when your AI agent ingests content from untrusted external sources — scraped web pages, third-party tool outputs, MCP responses, A2A payloads, or inbound emails — and you need to ensure that content does not contain hidden prompt injections or jailbreak instructions before your agent processes it. Prefer this over generic content filters when the threat model is specifically adversarial LLM manipulation rather than spam or malware.

• Empty or missing 'text' parameter returns a 400 validation error
• Extremely long payloads may be truncated or timeout
• Payment failure (HTTP 402) if x402 USDC micropayment is not completed
• False negatives on novel or obfuscated injection techniques not yet in detection ruleset
• Non-textual binary input may not be parsed correctly