Repository navigation
openssl 3.6.4 (11 CVEs, 2 Critical) - #710
Conversation
openssl 3.6.3 matches 11 advisories — 2 Critical, 8 High, 1 Medium — and 3.6.4 (2026-08-25) fixes every one of them. Checked rather than assumed: the 11 CVEs the scan reports against 3.6.3 and the 11 CVEs named in the 3.6.4 release notes are the SAME SET, with nothing left over on either side. CVE-2026-63073 (9.8) CVE-2026-75803 (9.1) — Critical CVE-2026-14456 -14457 -18798 -54874 -54876 -63072 -63075 -63076 — High CVE-2026-63074 — Medium These are the same upstream vulnerabilities as #709, reaching us through a second packaging path: that PR fixes the copy inside the Alpine minirootfs, this fixes our own openssl package. One upstream advisory set, two places to bump. No version inversion and no jump to 4.x. OpenSSL 4.0.2 exists, but 3.6.4 is the fix for our line, and Alpine's 3.5.8 is the LTS-branch backport of the same CVEs — both lines were patched, we were one patch behind on ours. pcre2 10.47 -> 10.48 is bundled deliberately, not opportunistically. Its advisory yield is small and stated honestly: of pcre2's 7 advisories 10.48 clears exactly ONE, the LOW GHSA-q7rw-r7qq-2hx6. The HIGH OSV-2026-343 is commit-ranged and its fix commit e19e76ad is NOT an ancestor of the 10.48 tag (checked via compare: 10.48 is behind it), so 10.48 does not clear it. The remaining 5 have no upstream fix at all. The reason to bundle is the REBUILD, not the yield: openssl and pcre2 share git, nginx, wget and rizin, so one cascade instead of two. Both tarballs verified byte-identical against upstream before mirroring: openssl c6b94124bb76ac5f8aa80de121e0f922a93d3bbf1be478bd50ebc36a30dc1db1 pcre2 b6c68fdf6f3ac31388b50aa89ff0fc49c00c987c16e7b5146491d12003f2c8ed Not built locally: `min session activate` on this worktree hangs on exec, which is the symptom gominimal/inbox#693 / #690 describe. Left to CI's minimal-check, which does a real build. openssl has 38 direct importers and pcre2 7, so the rebuild is wide — worth a reviewer's eye on the cascade rather than mine alone. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Essentials Run ID: 📒 Files selected for processing (2)
Included review availability: 0 reviews are currently available. Your included PR review attempts over the past 7 days set your current allowance at 1 review per hour. 📝 WalkthroughWalkthroughThe OpenSSL package moves to version 3.6.4. The PCRE2 package moves to version 10.48. Both definitions update their source archive SHA-256 checksums. ChangesPackage source refreshes
Priority: ⬆️ High Estimated code review effort: 1 (Trivial) | ~5 minutes Change: Bug fix Merge Risk: ⚪ Minimal · up to The dependency refresh introduces no identified merge-blocking behavior or risk. 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
Correcting myself: pcre2 is worth far more than I claimedI wrote above that 10.48 "clears exactly ONE, the LOW Measured by actually running the scanner against both trees rather than reading the raw advisory JSON: 7 of 8 clear. Only Why I got it wrong: I queried Combined effectFor So the bundling argument is no longer only about amortising the rebuild — pcre2 carries real security value on its own. |
#698 (open since 2026-09-15, green, mergeable) sets pcre2 to 10.48 with the identical sha256 b6c68fdf, and also carries xz 5.8.3 -> 5.8.4. I cut this PR without checking the open queue first, which duplicated it and would have put two PRs on packages/pcre2/build.ncl. This PR is now openssl-only, which is its unique contribution. The pcre2 half of the hunk fix rides #698. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Scope reduced: this PR is now openssl-onlyI cut this without checking the open PR queue first. #698 (open since 2026-09-15, green, mergeable) already bumps pcre2 to 10.48 with the identical sha256 Duplicating it would have put two PRs on That does not change the hunk outcome, only which PR delivers which half:
The "one cascade instead of two" argument in the description no longer applies to this PR — it now rebuilds openssl's 38 importers only. |
Why
openssl3.6.3 matches 11 advisories — 2 Critical, 8 High, 1 Medium — and 3.6.4 (released 2026-08-25) fixes every one.Checked rather than assumed: the 11 CVEs
pkgmgr vulns --package opensslreports against 3.6.3 and the 11 CVEs named in the 3.6.4 release notes are the same set, with nothing left over on either side.This is the second half of pkgs#709
These are the same upstream vulnerabilities, reaching us through two packaging paths:
libcrypto3/libssl33.5.7-r0 → 3.5.8-r0)opensslpackage (3.6.3 → 3.6.4)One upstream advisory set, two places to bump. Found via the transitive view on
minimal.dev/pkgs/hunk—hunkitself is clean, but inherits all of these throughgit.No version inversion, and no jump to 4.x. OpenSSL 4.0.2 (and 4.1.0-alpha1) exist, but 3.6.4 is the fix for our line. Alpine's 3.5.8 is the LTS-branch backport of the same CVE set — both lines got patched; we were one patch behind on ours.
pcre2 is bundled for the rebuild, not the yield
Stating this plainly so nobody reads it as a security win it isn't. Of pcre2's 7 advisories, 10.48 clears exactly one — the LOW
GHSA-q7rw-r7qq-2hx6:OSV-2026-343(HIGH) is commit-ranged, and its fix commite19e76adis not an ancestor of thepcre2-10.48tag (comparereports 10.48 behind it), so 10.48 does not clear it.The reason to bundle is the cascade: openssl and pcre2 share
git,nginx,wgetandrizin, so this is one rebuild instead of two.Verification
Both tarballs verified byte-identical against upstream before mirroring:
Diff is minimal — version + sha256 only, no license churn (askalono misreads OpenSSL's license as "Pixar"; it did not get written).
Not built locally.
min session activateon this worktree hangs on everyexec— the symptom gominimal/inbox#693 / #690 describe. Left to CI'sminimal-check, which does a real build.Reviewer note: the cascade is wide
openssl has 38 direct importers, pcre2 has 7:
That is a big rebuild and deserves a reviewer's eye on the cascade rather than mine alone.
Why this didn't auto-update (worth its own issue)
opensslis not base-soup (noreplace_on_cycle), so that isn't the reason. The nightly auto-fix triage has loggedopened=0every night, withskip_no_vuln_cleared=117as its dominant bucket — and every one of openssl's advisories carries 324 commit-SHA fixes and zero version-shaped fixes (all GIT ranges), so a version-based "would this clear?" test cannot prove 3.6.4 helps.I can't confirm openssl's bucket from the logs, because skips are only ever counted in aggregate, never named — which is the other half of the problem.
🤖 Generated with Claude Code
Summary by CodeRabbit