Make mime_find_header_token return a Vec directly as callers
turned it into a Vec.
This way, we do not need sections_values arg anymore.
Also do not build the complete hashmap of all tokens, when
we are just looking for one token. Instead, iterate the
token until we find the right name, and directly return its value.
This changes the behavior in case of repetitions as we are now
using the first token instead of the last one.
Fixes quoted unescaping as mime_parse_value_delimited does
the escaping itself the right way and returns a Vec
These API changes will be useful to support rfc2231 part 4 about
charset and language.
Ticket: 9157
To make cargo audit happy
Crate: zstd
Version: 0.13.3
Title: Data from an abandoned stream leaks into the next stream on a reused context
Date: 2026-10-16
ID: RUSTSEC-2026-0391
URL: https://rustsec.org/advisories/RUSTSEC-2026-0391
Solution: Upgrade to >=0.14.3
DCERPC REQUEST/RESPONSE records can have their stub data fragmented
across multiple PDUs. The flags that convey the state of the current PDU
are as follows:
PFC_FIRST_FRAG: first fragment of (fragmented) data
PFC_LAST_FRAG: last fragment of (fragmented) data
PFC_FIRST_FRAG && PFC_LAST_FRAG: no fragmentation
Consider a REQUEST/RESPONSE complete only when the PFC_LAST_FRAG flag is
found to be set.
Ticket: 9240
SCFTPFreeResponseLine gated the release of the code buffer on a null
test of the response pointer, so the code buffer had no check of its
own. Neither check could fire: parse_response_line sets both pointers
from Box::into_raw on a boxed slice, which never returns null, and C
code obtains an FTPResponseLine only from SCFTPParseResponseLine. The
comment on the code field claimed the pointer may be null; a line with
no status code gets an empty buffer with code_length 0 instead.
Remove both null checks, note why they are unnecessary, and correct the
field comment.
Ticket: 8803
parse_response_line allocates the code buffer with Box::into_raw on a
boxed slice, but SCFTPFreeResponseLine released it by rebuilding a
Vec<u8> with capacity code_length. Vec::from_raw_parts accepts any
global-allocator pointer whose size and alignment match, and both paths
compute the same layout for a byte slice, so the old free was sound. It
differed only from how the response buffer is released.
Release the code buffer through Box::from_raw on a slice pointer, so
both buffers are freed the same way they were allocated.
Ticket: 8803
In case a keyword should work in firewall mode, with firewall rules
only. The engine errors out if threat detection rules use the given keyword.
Part of
Ticket #9041
An empty SETTINGS frame (an ACK, or a SETTINGS without entries) opened
the settings array and closed it without items, producing a record the
eve schema rejects (settings has minItems 1). Skip the frame instead; a
tx whose only content is an empty SETTINGS frame is then not logged at
all, matching the empty headers handling.
Exposed by the flow-end flush of IDS-dropped flows: the dropped flow in
the drop-protocol-change test carries such a frame.
AppLayerParserGetTxEndState() replaces the remaining copies of the
transaction end state computation in the firewall tx setup, the
app-layer-state and app-layer-event keywords and the completion check.
One tolerated a missing tx data pointer, the others asserted or
dereferenced it, so they could disagree.
Move DetectTxCompleted() above its first use while there, so it no
longer needs a forward declaration, and shorten its comment.
Ticket: #8944.
DetectEngineInspectGenericList returned NO_MATCH for every keyword miss,
also when the tx had moved past the phase the engine is registered at.
Unlike the buffer engines it never produced a terminal no match, so a
firewall LTE rule using such a keyword (tls.version on a hook) stayed
provisional and was accepted for the rest of the session.
Make a miss terminal at P + 1. This engine also backs the lua
on-request/on-response hooks and the tls_cert_*, dnp3/dnp3_ind and
ftpdata/ftp mode keywords, so a plain IDS rule using them keeps its
verdict once the tx has moved past the registered phase.
Export the parser's end state computation as AppLayerParserGetTxEndState()
here, so the version keyword can use it; the remaining call sites are
converted later.
Ticket: #8944.
banner_wait_eol only recorded that a banner line of 256 bytes or
more had arrived without EOL; it was not an active phase. The
direction kept reparsing the open line in place, so a rule or
firewall policy pointing at the state acted on a parked, not an
active, direction.
Move the condition to the event channel it already had (the
one-shot ssh.long_banner event) and key the continuation off an
explicit banner_published latch (set at the banner publish
sites): a direction with an open line stays in the banner state,
the line is consumed greedily until the EOL arrives, and the line
completion takes the normal banner-to-kex transition.
The state scale becomes dense: banner(0) kex(1) session(2),
completion done(3). request_banner_wait_eol /
response_banner_wait_eol no longer load: aliasing them to banner
would silently turn a long-banner rule into an any-banner rule.
Firewall rules that acted at the removed state must move to the
ssh.long_banner event or the banner state; and since the progress
gap between banner and kex is gone, the default-policy sweep no
longer drops a clean flow at the server banner.
Ticket: #9046.
Philippe Antoine
Shivani Bhardwaj
Jason Ish
Jeff Lucovsky
Juliana Fajardini
Victor Julien