Anthropic
Put proxshield in front of the Anthropic Messages API.
proxshield handles POST /v1/messages (streaming and non-streaming) and POST /v1/messages/count_tokens.
TypeScript
Section titled “TypeScript”import Anthropic from "@anthropic-ai/sdk";
const anthropic = new Anthropic({ baseURL: "http://localhost:8080" });Python
Section titled “Python”from anthropic import Anthropic
client = Anthropic(base_url="http://localhost:8080")Or set ANTHROPIC_BASE_URL=http://localhost:8080.
What gets scanned
Section titled “What gets scanned”| Part of the request | Redacted | Checked for injection |
|---|---|---|
system (string or text blocks) |
yes | no |
user text |
yes | yes |
assistant text and tool_use input |
yes | no |
tool_result content (string or text blocks) |
yes | yes, a few sentences at a time |
document blocks with a text source |
yes | yes |
In replies, text blocks and tool_use input are restored. In streams, text_delta and input_json_delta events are restored, with JSON escaping for tool input. Thinking blocks are passed through untouched so their signatures stay valid.
count_tokens is counted on the redacted request, so the original values never reach Anthropic for that call either.
When a request is blocked
Section titled “When a request is blocked”{ "type": "error", "error": { "type": "invalid_request_error", "message": "Possible prompt injection in a tool result (score 0.98)." }}