diegosouzapw/OmniRoute · error

SECURITY_001

SECURITY_001

Error message

Request blocked: potential prompt injection detected

What it means

Error "Request blocked: potential prompt injection detected" thrown in diegosouzapw/OmniRoute.

Source

Thrown at src/app/api/v1/responses/route.ts:156

    } catch (error) {
      console.error("[SECURITY] Injection guard error:", error);
      return finishAdmission(
        new Response(JSON.stringify({ error: "Security check failed" }), {
          status: 500,
          headers: { "Content-Type": "application/json" },
        })
      );
    }

    const { blocked, result } = guardResult;
    if (blocked) {
      return finishAdmission(
        new Response(
          JSON.stringify({
            error: {
              message: "Request blocked: potential prompt injection detected",
              type: "injection_detected",
              code: "SECURITY_001",
              detections: result.detections.length,
            },
          }),
          { status: 400, headers: { ...CORS_HEADERS, "Content-Type": "application/json" } }
        )
      );
    }
    if (result.flagged) {
      try {
        request.headers.set("X-Injection-Flagged", "true");
        request.headers.set("X-Injection-Detections", String(result.detections.length));
      } catch {
        // Detection already ran; metadata propagation is best-effort.
      }
    }

    // Codex CLI (wire_api="responses") consumes this endpoint over SSE and its reqwest
    // client drops the connection if no bytes arrive within ~5s. Keep the connection

View on GitHub (pinned to a179ffed5b)

When it happens

Trigger: Thrown at src/app/api/v1/responses/route.ts:156 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of diegosouzapw/OmniRoute@a179ffed5b (2026-08-25). Data as JSON: /api/errors/137c1c9b37c16be2. Report an issue: GitHub.