Compare commits

..

1 Commits

Author SHA1 Message Date
Xavier Roche
d69b0b1426 CodeQL: exclude libtest demos and src/proxy from scanning
libtest/ holds demo callback samples that aren't part of libhttrack, and
src/proxy/ is ProxyTrack, a separate legacy binary with no auth surface whose
recv/cache-parse code trips the taint queries by design. Together they account
for ~26 alerts that are false-positive or by-design. Exclude both so the
dashboard tracks the engine, where the queries earn their keep.

Genuine bugs found in that code are fixed on their own, independent of scanning.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Signed-off-by: Xavier Roche <roche@httrack.com>
2026-07-15 21:08:41 +02:00
5 changed files with 13 additions and 163 deletions

View File

@@ -2696,12 +2696,9 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
int dispo = 0;
// probe the resolved address list once per fresh connect (cache hit:
// the host was resolved when this connect was opened). Not under a
// proxy: the socket dials the proxy, so resolving the origin here leaks
// its DNS and lets a proxy-connect failure fall back to dialing it
// direct.
// the host was resolved when this connect was opened)
if (cf->addr_count < 0 && back[i].r.soc != INVALID_SOCKET &&
!back[i].r.is_file && !back[i].r.req.proxy.active) {
!back[i].r.is_file) {
SOCaddr scratch[HTS_MAXADDRNUM];
cf->addr_count = hts_dns_resolve_all(opt, back[i].url_adr, scratch,
@@ -3313,26 +3310,16 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
back[i].chunk_blocksize = -1; /* ending */
back[i].r.totalsize += chunk_size; // noter taille
if (back[i].r.adr != NULL || !back[i].r.is_write) { // Not to disk
// totalsize sums attacker-declared chunk sizes; past
// 2GB the (size_t) cast below truncates on 32-bit and
// under-allocates. Mark the chunk invalid so the shared
// error path tears the transfer down.
if (back[i].r.totalsize > INT32_MAX) {
hts_log_print(opt, LOG_WARNING,
"Chunked resource too large for %s%s",
back[i].url_adr, back[i].url_fil);
chunk_size = -1;
} else {
back[i].r.adr = (char *) realloct(
back[i].r.adr, (size_t) back[i].r.totalsize + 1);
if (!back[i].r.adr) {
if (cache->log != NULL) {
hts_log_print(opt, LOG_ERROR,
"not enough memory (" LLintP
") for %s%s",
(LLint) back[i].r.totalsize,
back[i].url_adr, back[i].url_fil);
}
back[i].r.adr =
(char *) realloct(back[i].r.adr,
(size_t) back[i].r.totalsize + 1);
if (!back[i].r.adr) {
if (cache->log != NULL) {
hts_log_print(opt, LOG_ERROR,
"not enough memory (" LLintP
") for %s%s",
(LLint) back[i].r.totalsize,
back[i].url_adr, back[i].url_fil);
}
}
}

View File

@@ -1,18 +0,0 @@
#!/bin/bash
# A well-formed Transfer-Encoding: chunked response mirrors intact: the chunk
# automaton (htsback.c) joins the bodies and the 2GB in-RAM cap stays quiet.
# The 76-char run spans a 64-byte chunk boundary (only contiguous once joined);
# a CR anywhere would be leftover framing; '</body>' proves no truncation.
set -euo pipefail
: "${top_srcdir:=..}"
bash "$top_srcdir/tests/local-crawl.sh" --errors 0 \
--found 'chunked/page.html' \
--file-matches 'chunked/page.html' \
'chunk-body chunk-body chunk-body chunk-body chunk-body chunk-body chunk-body' \
--file-matches 'chunked/page.html' '</body>' \
--file-not-matches 'chunked/page.html' $'\r' \
--log-not-found 'too large' \
httrack 'BASEURL/chunked/index.html'

View File

@@ -1,93 +0,0 @@
#!/bin/bash
#
# A crawl through a proxy must never resolve or dial the origin itself: the proxy
# does that. A dead proxy + a multi-address origin used to fall back to dialing
# the origin direct (bypassing the proxy, leaking its DNS and IP). The decoy
# origin here must therefore receive nothing.
set -euo pipefail
: "${top_srcdir:=..}"
# shellcheck source=tests/testlib.sh
. "$top_srcdir/tests/testlib.sh"
if test "${V6_SUPPORT:-}" == "no"; then
echo "no IPv6 support (resolver override compiled out), skipping"
exit 77
fi
python=$(find_python) || {
echo "python3 missing, skipping"
exit 77
}
server=$(nativepath "$top_srcdir/tests/local-server.py")
root=$(nativepath "$top_srcdir/tests/server-root")
tmpdir=$(mktemp -d)
serverpid=
cleanup() {
stop_server "$serverpid"
rm -rf "$tmpdir"
return 0
}
trap cleanup EXIT
# decoy origin: it must stay silent. LOCAL_SERVER_VERBOSE logs any request it gets.
LOCAL_SERVER_VERBOSE=1 "$python" "$server" --root "$root" --bind 127.0.0.1 \
>"$tmpdir/srv.out" 2>"$tmpdir/srv.err" &
serverpid=$!
port=
for _ in $(seq 1 50); do
line=$(head -n1 "$tmpdir/srv.out" 2>/dev/null || true)
if test "${line%% *}" == "PORT"; then
port="${line#PORT }"
break
fi
kill -0 "$serverpid" 2>/dev/null || {
echo "server exited early: $(cat "$tmpdir/srv.err")"
exit 1
}
sleep 0.1
done
test -n "$port" || {
echo "could not discover server port"
exit 1
}
# a proxy port nothing listens on: grab a free one and let it close (refuses).
deadproxy=$("$python" -c \
'import socket; s=socket.socket(); s.bind(("127.0.0.1",0)); print(s.getsockname()[1]); s.close()')
# origin resolves to two addresses so a fallback would have a second to dial;
# 127.0.0.1 (the decoy) is the one the old bypass reached.
out="$tmpdir/crawl"
HTTRACK_DEBUG_RESOLVE="decoyhost:127.0.0.2,127.0.0.1" \
httrack "http://decoyhost:$port/simple/basic.html" -O "$out" \
-P "127.0.0.1:$deadproxy" -c1 --robots=0 --timeout=5 --retries=0 --quiet -Z \
>"$tmpdir/log" 2>&1
log="$out/hts-log.txt"
# the origin must have seen no connection (no leak/bypass)
if grep -qE '"(GET|POST|HEAD|CONNECT) ' "$tmpdir/srv.err"; then
echo "FAIL: origin was contacted directly, bypassing the proxy"
cat "$tmpdir/srv.err"
exit 1
fi
# the crawl must fail at the proxy (proves it really tried the proxy, not a no-op)
grep -q 'Connect Error' "$log" || {
echo "FAIL: expected a proxy connect error"
cat "$log"
exit 1
}
# and it must not have tried an origin-address fallback under the proxy
if grep -q "trying next address" "$log"; then
echo "FAIL: fell back to an origin address under a proxy"
cat "$log"
exit 1
fi
echo "OK: a dead proxy fails cleanly without dialing the origin"

View File

@@ -131,8 +131,6 @@ TESTS = \
51_local-update-codec.test \
52_local-socks5.test \
53_local-proxytrack-cache-corrupt.test \
54_local-update-truncate-purge.test \
55_local-chunked.test \
56_local-proxy-noleak.test
54_local-update-truncate-purge.test
CLEANFILES = check-network_sh.cache

View File

@@ -1215,28 +1215,6 @@ class Handler(SimpleHTTPRequestHandler):
if self.command != "HEAD":
self.wfile.write(body)
def route_chunked_index(self):
self.send_html('\t<a href="page.html">chunked</a>\n')
def route_chunked_page(self):
# Transfer-Encoding: chunked over many small chunks: drives the engine's
# chunk automaton (htsback.c). The mirrored file must equal the joined
# chunk bodies, so the 2GB in-RAM cap doesn't fire on ordinary traffic.
blob = big_html("chunked", "<p>" + "chunk-body " * 300 + "</p>")
self.protocol_version = "HTTP/1.1"
self.send_response(200)
self.send_header("Content-Type", "text/html; charset=utf-8")
self.send_header("Transfer-Encoding", "chunked")
self.send_header("Connection", "close")
self.end_headers()
if self.command == "HEAD":
return
step = 64
for off in range(0, len(blob), step):
piece = blob[off : off + step]
self.wfile.write(b"%X\r\n" % len(piece) + piece + b"\r\n")
self.wfile.write(b"0\r\n\r\n")
# Content-Disposition naming: the attachment filename replaces the
# URL-derived name; path components in it are stripped (RFC 2616).
CDISPO_NAMES = {
@@ -1576,8 +1554,6 @@ class Handler(SimpleHTTPRequestHandler):
"/crange206mem/blob.bin": route_crange206mem,
"/size/index.html": route_size_index,
"/size/oversize.bin": route_size_oversize,
"/chunked/index.html": route_chunked_index,
"/chunked/page.html": route_chunked_page,
"/errpage/index.html": route_errpage_index,
"/errpage/good.html": route_errpage_good,
"/errpage/missing.html": route_errpage_missing,