A2A Indirect Prompt-Injection & Jailbreak Firewall

Choose this endpoint when your AI agent pipeline ingests untrusted external content — scraped web pages, emails, MCP tool responses, or A2A payloads — and you need a lightweight, per-call security layer to detect and strip hidden prompt injections or jailbreak attempts before that content reaches your LLM. Prefer it over manual filtering when operating in adversarial or semi-trusted environments where third-party data sources may be weaponized against your agent.

• Empty or missing 'text' parameter returns a 400 validation error
• Extremely large payloads may be truncated or rejected
• False negatives possible for novel or obfuscated injection techniques
• False positives may flag legitimate instructions embedded in content
• Service unavailability returns a 5xx error; retry recommended
• Payment failure via x402 returns 402 Payment Required