Files
LocalAI/pkg/utils/base64.go
T
mudler-agentandEttore Di Giacinto 756b019ce4 [httpclient] validate redirect targets and pin dialed addresses for user URLs (#12853)
fix(httpclient): validate redirect targets and pin dialed addresses for user URLs

Clients that fetch user-supplied URLs followed redirects without checking
the target, so a public host could send them to a loopback, link-local
or private address. The host was also resolved twice, once to validate
it and once to connect, so a changing DNS answer could bypass the check.

Add httpclient.WithExternalOnly. It validates every redirect hop against
the external URL policy and, for the default transport, resolves the
host, refuses it if any address is non-public, and dials the validated
address. Environment proxies are not used for such clients.

Move the policy (ValidateExternalURL, IsPublicIP) into pkg/httpclient
so it can be used without an import cycle; pkg/utils keeps delegating
to it. IsPublicIP now also refuses 100.64.0.0/10, 0.0.0.0/8,
192.0.0.0/24, 198.18.0.0/15, 240.0.0.0/4, multicast, and NAT64
addresses that wrap a non-public IPv4 address.

Use the option for the base64, image, audio and video downloads, and
drop the video client's own per-hop check.

Assisted-by: Claude Code:claude-haiku-5-5

Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
2026-10-23 11:54:42 +02:00

61 lines
1.8 KiB
Go

package utils
import (
"encoding/base64"
"fmt"
"io"
"regexp"
"strings"
"time"
"github.com/mudler/xlog"
"github.com/mudler/LocalAI/pkg/httpclient"
)
var base64DownloadClient = httpclient.NewWithTimeout(30*time.Second, httpclient.WithFollowRedirects(), httpclient.WithExternalOnly())
// Match `data:<mime>[;param=value...];base64,` — browser-produced data URIs
// often carry codec/charset params between the mime type and `;base64,`
// (e.g. MediaRecorder's `data:audio/webm;codecs=opus;base64,...`). The old
// `([^;]+)` form only tolerated exactly one segment, so anything with
// extra params failed the strip and tripped the downstream base64 decoder
// on the `data:` literal.
var dataURIPattern = regexp.MustCompile(`^data:[^,]+?;base64,`)
// GetContentURIAsBase64 checks if the string is an URL, if it's an URL downloads the content in memory encodes it in base64 and returns the base64 string, otherwise returns the string by stripping base64 data headers
func GetContentURIAsBase64(s string) (string, error) {
if strings.HasPrefix(s, "http") || strings.HasPrefix(s, "https") {
if err := ValidateExternalURL(s); err != nil {
return "", fmt.Errorf("URL validation failed: %w", err)
}
// download the image
resp, err := base64DownloadClient.Get(s)
if err != nil {
return "", err
}
defer resp.Body.Close()
// read the image data into memory
data, err := io.ReadAll(resp.Body)
if err != nil {
return "", err
}
// encode the image data in base64
encoded := base64.StdEncoding.EncodeToString(data)
// return the base64 string
return encoded, nil
}
// Match any data URI prefix pattern
if match := dataURIPattern.FindString(s); match != "" {
xlog.Debug("Found data URI prefix", "prefix", match)
return strings.Replace(s, match, "", 1), nil
}
return "", fmt.Errorf("not valid base64 data type string")
}