hyperhive/swarm-nats-auth/src/request.rs

//! Decoding the server's authorization request.
//!
//! The payload on `$SYS.REQ.USER.AUTH` is a NATS JWT: three base64url
//! (no-pad) segments separated by `.`. The middle segment is the claim set,
//! and its `nats` object carries what the client presented.
//!
//! Decoding is deliberately hand-rolled while *minting* is not. The asymmetry
//! is the point: producing a signed artifact wrongly is silent — the server
//! rejects it and the reason is on the far side — whereas mis-parsing an
//! inbound one fails loudly on the very next field. `nats-jwt` is also
//! encode-only, so there is nothing to reuse here.

use anyhow::{Context, Result, bail};
use serde::Deserialize;

/// The subset of an `authorization_request` claim this responder acts on.
#[derive(Debug, Deserialize)]
pub struct AuthRequest {
    /// Everything the connecting client sent in its `CONNECT` line.
    pub connect_opts: ConnectOpts,
    /// Ephemeral user nkey the server minted for this connection. The user
    /// JWT we issue must be addressed to it, not to any name the client
    /// chose — a client-supplied identity is a request, not a fact.
    pub user_nkey: String,
    /// Server this request came from; echoed back in the response so a
    /// reply cannot be replayed at a different server in the cluster.
    pub server_id: ServerId,
}

/// The client-controlled half of the request. Every field here is attacker
/// input: it is whatever the connecting client typed, not something the
/// server vouches for.
///
/// The wire object also carries `user` / `pass` when a client authenticates
/// that way. They are deliberately **not** modelled: the swarm authenticates
/// against the `IdP`, and a field that exists in this struct is a field
/// someone will eventually branch on.
#[derive(Debug, Deserialize)]
pub struct ConnectOpts {
    /// Bearer token, when the client presented one. The only field this
    /// responder acts on.
    #[serde(default)]
    pub auth_token: Option<String>,
}

#[derive(Debug, Deserialize)]
pub struct ServerId {
    pub id: String,
}

/// Split a NATS JWT and deserialize its claim set's `nats` object.
///
/// The signature is **not** verified here — see the module docs on
/// `main.rs` for why that is a decision and not an oversight.
pub fn decode(payload: &[u8]) -> Result<AuthRequest> {
    /// Only the `nats` object is modelled; `iss`/`sub`/`exp` are the server's
    /// business, and claiming to understand fields we do not act on would
    /// invite someone to trust them.
    #[derive(Deserialize)]
    struct Claims {
        nats: AuthRequest,
    }

    let text = std::str::from_utf8(payload).context("auth request is not utf-8")?;
    let mut parts = text.split('.');
    // Exactly three segments: a fourth means this is not the shape we think
    // it is, and a lenient split is how a parser starts accepting things the
    // producer never meant to send.
    let (Some(_header), Some(claims), Some(_sig), None) =
        (parts.next(), parts.next(), parts.next(), parts.next())
    else {
        bail!("auth request is not a three-segment JWT")
    };
    let raw = base64_url_decode(claims).context("claim segment is not base64url")?;

    let claims: Claims =
        serde_json::from_slice(&raw).context("claim segment is not the expected JSON")?;
    Ok(claims.nats)
}

/// base64url without padding, as JWT uses. Written out rather than pulled in:
/// `data-encoding` is already in the tree via `nkeys`, but its no-pad URL
/// alphabet spec is one line either way and this keeps the direct dependency
/// list honest about what this crate actually needs.
fn base64_url_decode(s: &str) -> Result<Vec<u8>> {
    data_encoding::BASE64URL_NOPAD
        .decode(s.as_bytes())
        .context("base64url decode")
}

#[cfg(test)]
mod tests {
    use super::*;

    fn jwt_with(claims: &str) -> String {
        let b = |s: &str| data_encoding::BASE64URL_NOPAD.encode(s.as_bytes());
        format!("{}.{}.{}", b("{}"), b(claims), b("sig"))
    }

    #[test]
    fn decodes_a_token_request() {
        let req = decode(
            jwt_with(
                r#"{"nats":{"connect_opts":{"auth_token":"t0k"},
                   "user_nkey":"UABC","server_id":{"id":"NDEADBEEF"}}}"#,
            )
            .as_bytes(),
        )
        .expect("decode");
        assert_eq!(req.connect_opts.auth_token.as_deref(), Some("t0k"));
        assert_eq!(req.user_nkey, "UABC");
        assert_eq!(req.server_id.id, "NDEADBEEF");
    }

    #[test]
    fn a_request_without_a_token_is_still_well_formed() {
        // An anonymous connect must parse, then be *rejected* by policy —
        // not fail to parse. Conflating "malformed" with "unauthorized"
        // loses the ability to tell a broken server from an attacker.
        let req = decode(
            jwt_with(r#"{"nats":{"connect_opts":{},"user_nkey":"U","server_id":{"id":"N"}}}"#)
                .as_bytes(),
        )
        .expect("decode");
        assert!(req.connect_opts.auth_token.is_none());
    }

    #[test]
    fn rejects_a_payload_that_is_not_a_jwt() {
        assert!(decode(b"not-a-jwt").is_err());
        assert!(decode(b"two.parts").is_err());
        assert!(decode(b"four.parts.here.too").is_err());
    }
}