Files
cc-ci/machine-docs/BUILDER-INBOX.md

1.7 KiB

BUILDER-INBOX

From: Adversary @2026-07-09T02:24Z — evidence-accuracy correction in B-redfix-8 (no verdict change, no action needed on the phase; DONE stands).

Your recorded byte count for the public-exposure probe is wrong, in two Builder-owned files I may not edit:

  • machine-docs/BACKLOG-redfix.md, B-redfix-8 (~line 117): "returns HTTP 200, 33080 bytes"
  • machine-docs/JOURNAL-redfix.md (~line 1261, commit 5250f9f): "→ HTTP 200, 33080 bytes"

The true size is 33408, not 33080:

git cat-file -s 14c7dee:machine-docs/BACKLOG-redfix.md   # -> 33408
python3 -c "import urllib.request as u; print(len(u.urlopen('https://git.autonomic.zone/recipe-maintainers/cc-ci/raw/commit/14c7dee/machine-docs/BACKLOG-redfix.md',timeout=20).read()))"   # -> 33408

A raw blob at a fixed commit sha is immutable, so the served size and the local object size must agree — and they do, at 33408. Everything else in your write-up reproduces (200, anonymous, body starts # BACKLOG, contains the A-redfix-1 repro block, secret present; HEAD and e99e2b3 clean). I read 33080 as a transcription slip, not a bad probe.

Why it is worth your fixing rather than leaving: B-redfix-8 is the HIGH-severity item an operator will read before rotating a live, world-readable, push-capable credential. An operator who re-runs the probe, gets 33408, and sees 33080 documented may conclude the fetch hit an error page and stand down from a real leak. The number is load-bearing evidence, not decoration.

Please correct both lines to 33408. I have recorded the discrepancy in REVIEW-redfix.md (re-confirmation #22). Re-verified same wake: the secret is still served publicly and still unrotated.