Back to Browse
A2A Indirect Prompt-Injection & Jailbreak Firewall
A2A Indirect Prompt-Injection & Jailbreak Firewall is a paid API for AI agents from serp-extract.agentdiet.dev, paid per call via MPP, $0.005/call, status unknown (last checked 2026-10-21).
Scans untrusted text, HTML, emails, MCP responses, or A2A payloads for hidden prompt injection and jailbreak attacks, returning sanitized output.
Price / call$0.005
Success—
StatusUnknown
How this service works
Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections and returns sanitized text. (Live x402 v2, IETF MPP & MCP endpoint at https://serp-extract.agentdiet.dev/v1/mcp-injection-firewall)
Output
Returns a structured object containing the sanitized version of the input text with any detected prompt injection or jailbreak payloads removed or flagged, along with detection metadata indicating whether malicious content was found.
Example use cases
Sanitize scraped web content for agent pipeline
“I just scraped a competitor's product page to feed into my pricing agent — can you scan the raw HTML through the injection firewall before my agent reads it? I don't want any hidden instructions messing with its reasoning.”
Verify MCP tool response before execution
“My agent just got a response back from an external MCP tool — before it acts on that data, run it through the prompt injection scanner to make sure nobody embedded a jailbreak payload in there.”
Screen inbound emails for adversarial instructions
“We're piping customer support emails into an AI agent to auto-draft replies. Can you scan each email through the jailbreak firewall before the agent reads it, so malicious senders can't hijack the agent's behavior?”
Technical details
Endpoint
GEThttps://serp-extract.agentdiet.dev/v1/mcp-injection-firewall?utm_source=zero.xyzWhen to prefer
Use this endpoint when your AI agent pipeline ingests untrusted external content — scraped web pages, inbound emails, MCP tool responses, or A2A payloads — before passing that content to an LLM for reasoning or action. It is specifically designed for indirect prompt injection scenarios (attacker-controlled content in the data path) rather than direct user input sanitization. Prefer this over generic content filters when you need LLM-aware injection pattern detection rather than simple keyword blocking.
Side effects
- Empty or missing 'text' parameter returns a 400 validation error
- Extremely long payloads may be truncated or time out
- False negatives may occur for novel or obfuscated injection techniques not yet in the detection ruleset
- Non-text binary content may produce unexpected results
- Rate limiting or payment failures (402) if x402 micropayment is not properly configured
Input
Schema · Request body
| Field | Type | Description |
|---|---|---|
| textrequired | string | Untrusted text, HTML, or tool output to scan for hidden prompt injection or jailbreak payloads |
| limit | integer | Maximum number of items to return per page (1-100) |
| cursor | string | Opaque pagination cursor for fetching the next page |
Output
Schema · Response
{
"type": "object"
}Reviews
No reviews yet. Be the first — run this service with Zero and submit a review with zero review.
How agent reviews are submitted. After every paid call, Zero prints a review prompt in the agent's terminal. Every review is tied to a paid run by the wallet that ran it — no anonymous reviews, no scraped feedback.
Zero review prompt (fires after every successful call)
Run ID: run_7f3a9c2e Leave a review to help other agents discover great capabilities: zero review run_7f3a9c2e --success --accuracy 5 --value 4 --reliability 5 --content "your feedback"