Skip to content

rsync: allow autoconf's C++11 eval( template in configure.sh (3.5.2, CVE-2026-119741) - #1323

Merged
bryan-minimal merged 1 commit into
mainfrom
rsync-pkgscan-allow
Nov 5, 2026
Merged

bryan-minimal merged 1 commit into
mainfrom
rsync-pkgscan-allow

Conversation

@bryan-minimal

@bryan-minimal bryan-minimal commented Nov 4, 2026 •

Copy link
Copy Markdown
Member

rsync: allow autoconf's C++11 eval( template in configure.sh

The nightly refused rsync 3.5.1 → 3.5.2 because pkgscan flagged configure.sh:2947, eval(, as Critical (CodeExecution). 3.5.2 fixes CVE-2026-119741, so the bump matters.

The finding is a false positive

Line 2947 is template <typename Ret, typename Fn> Ret eval(Fn f, Ret v). It sits in autoconf 2.72's stock C++11 test program, a C++ function named eval, not shell eval.

Why the whole tarball was checked, not just the line

configure.sh is generated and ships only in the tarball, which is where xz-utils hid its payload. Two more things called for care:

  • the whole file changed (3,458 diff lines);
  • since 3.5.1, releases are published by a new maintainer, steadytao (Zen Dodd), whose GitHub account is from January 2026. They self-merge without review.

What was checked (2026-11-04):

  • Mirror. The tarball is byte-identical to the one on download.samba.org, which is Samba team infrastructure separate from GitHub (sha256 a10d591825251e070f74c98df3daad195def4ed81b4a2de16169026aea33f6c8).

  • Source. Every git-tracked file in the tarball equals tag v3.5.2. Only generated files differ: configure.sh, aclocal.m4, config.h.in and the man pages.

  • Why configure.sh changed so much.

    • 3.5.1 was generated with Autoconf 2.73 / aclocal 1.19, and 3.5.2 with 2.72 / 1.17.
    • configure.ac gained only five checks: wchar.h, linux/ioprio.h, sys/syscall.h, mbrtowc and setpriority. These serve the new --nice option and the locale fixes.
    • config.h.in changes by exactly those five.
  • Payload markers. A scan for base64 blobs, curl/wget, /dev/tcp, hex escapes, LD_PRELOAD and ifunc finds the same 3 hits in 3.5.1 and 3.5.2.

  • Maintainer handover. tridge, the previous release manager, kept committing after it (2026-10-15). The NEWS line granting steadytao release authority was written by steadytao, so the handover itself has no independent confirmation.

  • Release signature. It verifies, checked with sequoia sq 1.5.0 (sq --home=none verify --signer-file … --signature-file …).

    • Signer: signing subkey 8EDF 88F4 731A 1E8B 45D6 7FBE 6909 546B 2C52 EC2D of Zen Dodd's primary key C0E1 0545 0570 4F75 7D92 5AB2 6A64 E8AA 2EFB CF5D (Ed25519, created 2026-04-08).
    • Key copies: keys.openpgp.org and keyserver.ubuntu.com serve the same key, with valid SHA-512 self-signatures.
    • 3.5.1: verifies with the same key.
    • Negative control: the 3.5.2 signature over the 3.5.1 tarball fails ("Message has been manipulated").
    • Fingerprint listing: rsync.samba.org/download.html names this fingerprint for releases from 3.5.1 on, and tridge's 9FEF 112D … 1BB2 4997 A853 5F6F for 3.4.0–3.5.0.

Not checked, or not independent:

  • Who vouches for the key. Nobody independent does, as far as I can find.
    • Zen Dodd added the download-page line naming the key on 2026-11-03 (ae68af9b, "website: prepare rsync 3.5.2", then 41bbd895). That was six weeks after 3.5.1 shipped signed by it. The site's source lives in the same repo.
    • No tridge commit, PR or issue mentions the key, Zen or a handover. I searched the git history (-S on the fingerprint) and his GitHub issues and PRs.
    • Neither keyserver copy carries a certification from tridge's key.
    • So the signature shows the holder of Zen's key made this tarball. It does not independently show that tridge handed over release authority. Asking tridge directly, for example on the rsync mailing list, would settle it.
  • A byte-for-byte autoconf 2.72 regeneration of configure.sh. That would settle it fully if a reviewer wants it.

Change

Adds packages/rsync/pkgscan-allow.toml with one entry, pinned to the 3.5.2 configure.sh sha256 (5619489…253b). Any later change to that file gates again. A match regrades the finding to Info and never hides it. Once this merges, the next nightly reopens the rsync update.

Not affected by #1113 (held), which would give allowlist files a security owner. Under today's CODEOWNERS any minimalist can approve this.

🤖 Generated with Claude Code

pkgscan flagged configure.sh:2947 eval( as Critical; it is autoconf
2.72's C++11 test program, not shell eval. Tarball verified against
download.samba.org and tag v3.5.2; details in the PR.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
@bryan-minimal
bryan-minimal requested a review from a team as a code owner November 4, 2026 21:26
@coderabbitai

coderabbitai Bot commented Nov 4, 2026 •

Copy link
Copy Markdown
Contributor

Explain Change →

No actionable comments were generated in the recent review.

Walkthrough

The rsync pkgscan allowlist now includes a SHA-256-pinned entry for matching eval( in configure.sh under the CodeExecution category.

Changes: rsync pkgscan allowance

Layer / File(s) Summary
Pinned pkgscan allowlist entry
packages/rsync/pkgscan-allow.toml
Adds an entry for configure.sh that matches eval( only when the file has the specified SHA-256. Comments describe the finding’s context and release comparison.

Estimated code review effort: 2 (Simple) | ~5 minutes

Suggested reviewers: mitodrummer

Merge Risk: Minimal · up to a5c7b

No actionable merge-blocking risk is established for the pinned allowance.

Pre-merge checks: Passed 4
Check name Status Explanation
Description Check Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check Passed The title clearly identifies the rsync allowlist change, the affected configure.sh template, the version, and the related CVE. It is specific and directly related to the main change.
Linked Issues check Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check Passed Check skipped because no linked issues were found for this pull request.
Finishing Touches
Generate unit tests (beta)
  • Commit to this branch
  • Create a new PR
  • Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts
Recent review info
Run configuration
Commits

Reviewing files that changed from the base of the PR and between 644809f and a5c7ba4.

Files selected for processing: 1
  • packages/rsync/pkgscan-allow.toml

Included review availability: This review used your included allowance. 0 included reviews remain after this review. Your included PR review attempts over the past 7 days set your current allowance at 1 review per hour.

@norrietaylor norrietaylor left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Scope matches the title. The PR adds one file, packages/rsync/pkgscan-allow.toml, with one entry. packages/rsync/build.ncl stays at 3.5.1, as the PR body states. So this PR does not ship the CVE-2026-119741 fix. The fix needs the later nightly update.

Clobber none. The file is new, and git show --stat shows 15 added lines and no other change.

Correctness the entry has the same shape as the five sibling allowlists. The three findings are all in the text of the record. The reason string contradicts the PR body on the release signature, and it states the regeneration as fact although nobody reproduced it. The header comment gives a regrade that does not match a Critical finding. The TOML keys and the pin mechanism look correct.

Decision for a maintainer the PR body says that nobody independent vouches for the new release key, and that nobody regenerated configure.sh byte for byte. This file is the place where a tarball-only payload hides. A person must accept that risk before merge. This review does not settle it.

Not checked the sandbox denied network access and access outside the checkout. I did not confirm the configure.sh sha256, line 2947, or the number of eval( hits in the 3.5.2 tarball. I did not read src/pkgscan/repo_allowlist.rs in pkgmgr-rs, so the regrade rule and the CodeExecution category name come from sibling files and the PR body. All tarball claims in the PR body are unverified here.

category = "CodeExecution"
pattern = "eval("
sha256 = "5619489284eb125cd1d77ad79860f80f0b902856f848baf749a6c34c96b7253b"
reason = "rsync 3.5.2. The match is autoconf 2.72's C++11 test program (`Ret eval(Fn f, Ret v)`), not shell eval. Tarball checked 2026-11-04: byte-identical to https://download.samba.org/pub/rsync/src/rsync-3.5.2.tar.gz (sha256 a10d5918...); every git-tracked file equals tag v3.5.2; the configure.sh diff from 3.5.1 is an autoconf 2.73 -> 2.72 regeneration plus five configure.ac checks (wchar.h, linux/ioprio.h, sys/syscall.h, mbrtowc, setpriority) that config.h.in mirrors exactly; payload-marker scan identical to 3.5.1. Release signature not verified (no gpg; the signer is a new maintainer, steadytao)."

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

low · The reason says the release signature is not verified, but the PR body says that it verifies with sq 1.5.0. The text is stale from before that check. The reason is the record that stays after merge, so the next triager reads the wrong state. Replace the last sentence with the real result: the signature verifies against Zen Dodd's key, and nobody independent vouches for that key. That second fact is the caveat that matters, and the file does not carry it. The other allowlists do not repeat this contradiction, so the fix is local.

category = "CodeExecution"
pattern = "eval("
sha256 = "5619489284eb125cd1d77ad79860f80f0b902856f848baf749a6c34c96b7253b"
reason = "rsync 3.5.2. The match is autoconf 2.72's C++11 test program (`Ret eval(Fn f, Ret v)`), not shell eval. Tarball checked 2026-11-04: byte-identical to https://download.samba.org/pub/rsync/src/rsync-3.5.2.tar.gz (sha256 a10d5918...); every git-tracked file equals tag v3.5.2; the configure.sh diff from 3.5.1 is an autoconf 2.73 -> 2.72 regeneration plus five configure.ac checks (wchar.h, linux/ioprio.h, sys/syscall.h, mbrtowc, setpriority) that config.h.in mirrors exactly; payload-marker scan identical to 3.5.1. Release signature not verified (no gpg; the signer is a new maintainer, steadytao)."

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

low · The reason states as fact that the configure.sh diff from 3.5.1 is an autoconf 2.73 -> 2.72 regeneration plus five checks. The PR body lists a byte-for-byte autoconf 2.72 regeneration under "Not checked". The evidence is version headers, the configure.ac changes, config.h.in and a marker scan. This is an inference, and it is the claim that excludes a tarball-only payload. Write what was done, for example "consistent with a regeneration, not reproduced byte for byte". Otherwise a later reader will take the file as proof that the 3,458 changed lines are clean.

@@ -0,0 +1,15 @@
# pkgscan triage for rsync (see pkgmgr-rs src/pkgscan/repo_allowlist.rs).
# Each entry is pinned to the whole file's sha256: any change to the file makes
# the finding gate again. A match regrades (High -> Info), never hides.

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

low · The header says a match regrades High -> Info, but the PR body says pkgscan graded this finding Critical. The sibling headers give Critical -> Medium (packages/atuin/pkgscan-allow.toml:3, packages/opencode/pkgscan-allow.toml:3, packages/plannotator/pkgscan-allow.toml:3). So this match probably lands at Medium, not Info, and the PR body claim "regrades the finding to Info" is probably wrong too. The line looks copied from the difftastic or async-profiler header. Confirm the grade in repo_allowlist.rs and correct the header. I did not read that file. If the finding is really High, correct the PR body in its place.

@bryan-minimal
bryan-minimal added this pull request to the merge queue Nov 5, 2026
Merged via the queue into main with commit 772de69 Nov 5, 2026
14 checks passed
@bryan-minimal
bryan-minimal deleted the rsync-pkgscan-allow branch November 5, 2026 18:48
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants