A2A Indirect Prompt-Injection & Jailbreak Firewall

Choose this endpoint when your AI agent pipeline ingests content from untrusted external sources — scraped web pages, inbound emails, MCP tool responses, or A2A payloads — and you need a lightweight, low-cost ($0.005/call) firewall step before passing that content to an LLM. Prefer this over general content moderation APIs when the threat model is specifically adversarial prompt injection and jailbreak attempts targeting AI agents, rather than general harmful content.

• Empty or missing 'text' parameter returns a validation error
• Extremely long payloads may be truncated or rejected
• Evasive encoding techniques (e.g., Unicode obfuscation) may reduce detection accuracy
• False positives on legitimate but unusual formatting patterns
• Service unavailability returns HTTP 402 or 5xx errors