Greptile P1: sedScriptParts stopped at -- and discarded the remaining
operands, so 'sed -- <script>' skipped script collection entirely. GNU sed
4.9 (verified): with no -e/--expression anywhere, the first operand after --
is the script and an s///e in it still executes.
The operands after -- are now collected as positionals, so the existing
first-positional-becomes-script rule applies. Operands after the script stay
file names (data). 2 regression tests pin both sides. Suite: 812/812.
Greptile P1 findings (both verified by running GNU sed against the hook):
1. Escaped replacements evade the check: GNU sed decodes \xHH, \oOOO, \dNNN,
case operations and unknown escapes like \g before executing an s///e
replacement or e operand. Scanning the raw text let \x67it decode to git.
Decoding that surface faithfully is out of scope, so any backslash in an
exec-bearing fragment now throws UnsupportedSedEscape and the hook blocks
with an explicit reason — mirroring the existing env -S escape precedent
instead of pretending to interpret sed. Escaped-newline continuations of an
e operand are refused by the same check.
2. Continued commands went unchecked: the e operand reader stopped at every
newline, but GNU sed joins escaped newlines into one operand. Now covered
by the same conservative refusal.
Also decomposes the sed readers into sub-50-line helpers per the repository
function-size rule (AGENTS.md): readSedDelimited, readSedCommand,
readSedExecute, readSedLineOperand, assertSedLiteral.
5 regression tests pin the escape paths and the benign boundary (a backslash
in a non-executing script stays data). Suite: 810/810.
CodeRabbit security review (Major, CWE-693) correctly identified that GNU sed
collects -e/--expression scripts from any argv position: a script option after
positional operands is still executed, so stopping the option walk at the first
positional let an e-flagged script hide behind it.
Verified against GNU sed 4.9 before fixing:
- 'sed -e s/x/y/ - -e s/y/X/e' runs X (the later -e executes)
- with any script option present, every positional is a file operand
sedScriptParts now walks the full argv, collects scripts from all -e/
--expression positions, and only promotes the first positional to the script
when no script option was given. Unknown options after positionals still fall
back to the opaque default.
4 regression tests pin the reported bypass paths (suite: 805/805).
Ported from the #3051 discussion (test intent, not the old scanner):
- A confidently-parsed sed invocation whose script contains no execution
construct is a pure text transformation: the script operand and every file
operand are data. This removes the specific false positives where file names
or non-executing scripts merely containing 'git ...' were blocked.
- The GNU sed `e` command (bare or with operand) and the `s` command with the
`e` flag run text through the shell. Their literal fragments (the s
replacement, the e operand) and any piped/redirected source are scanned as
real shell source, closing the `printf x | sed 's/x/git commit --no-verify/e'`
gap reported on 2026-10-09.
- Anything the literal parser cannot confidently read (addresses it cannot
consume, -f script files, -i suffix ambiguity, unknown options, expansion
residue) falls back to today's opaque default. No behavior changes for
unmodeled launchers.
- shell-scan.js is untouched and remains the canonical scanner.
Tests: 14 focused cases ported from the #3051 litmus set; full hook suite
801/801.
Drop the duplicate ECC_PREPUSH_RUN_CHECKS key now that main sets it,
refresh the skill-triggers registry digest, classify skill-host-compat
for pi/core, and bump the Turkish AGENTS.md counts the catalog sync
does not cover.
Each writer performs 30 write rounds to widen the race window. Drop the vacuous exitCode liveness assert and the swallowing mid-flight read; instead every wait-loop poll reads and validates the state, so torn reads fail loudly.
Assert dry-run install writes nothing under projectRoot too (cursor target writes there, not home). Rewrite the concurrent writeInstallState test with genuinely overlapping writers via async spawn plus done-file rendezvous, including a mid-flight read; sanitize rendezvous filenames for Windows.
Honor ECC_DRY_RUN=1 in install and repair arg parsing (previously only --dry-run flag worked, so ecc --dry-run install/repair silently performed real writes). Make writeInstallState atomic via writeFileAtomic (O_EXCL staging, fsync, cleanup on failure, atomic rename preserving previous state). Add writeInstallState failure/concurrency/symlink regression tests and disposable-home CLI dry-run regression tests for both global and subcommand forms.
Track illustrative scopes and retain their connectors so a contrastive
request or rejection for the current task ends the preceding example.
Preserve complete skill aliases, outer discussion guards, quoted task
qualifiers, and indirect citation protection for scored admission.
Invalidate older routing receipts and add resolver/launcher regressions
for request ordering, scope boundaries, aliases, and the reported P1.
Treat example-framing prefixes as indirect citations before checking
rejections, preserving genuine requests around illustrative instructions.
Keep e.g. together during clause splitting without rewriting e.g.js tokens.
Bump routing policy to v10 to invalidate v9 selections that loaded example
context. Cover resolver, launcher, instruction ordering, and receipt reuse.
Allow neutral imperative task preambles before an explicit skill request
without admitting final bare mentions, questions, or subject-led reports.
Keep rejection-list scoping intact and recognize must/ought questions.
Bump routing policy to v9 so an empty v8 receipt is reconsidered. Cover
resolver and launcher behavior and document the affected routing helpers.
Keep follow-up questions and reported instructions on the proposal path by
requiring recognized scopes and a direct request prefix for exact admission.
Preserve grouped rejections, personal negation, and genuine directives around
indirect discussion. Invalidate v7 receipts with routing policy v8.
Cover both Greptile reproductions and neighboring resolver/launcher cases,
including unlisted wording, nested reports, and grouped negative lists.
Limit negation to each independent directive after comma, and, or but.
Accept imperative requests with question punctuation while preserving true
questions, reported speech, and ordered rejections. Bump routing policy to
v7 so prior empty selections are reconsidered.
Add resolver and launcher regressions for the individual cases and their
combinations, including cached selections and actual context injection.
Validate env -S and --split-string escape syntax before shell scanning or
opaque fallback. Preserve literal single-quoted data and charge each
validation character against the shared input-proportional work budget.
Verified 787 focused cases and 290 real Git/config, harmless native env
and registered-routing controls. Keeps the prior paid-copy protection.
Co-authored-by: Nguyen Thanh Dat <ntdat812.dev@gmail.com>
Co-authored-by: Davemaina1 <dmain7015@gmail.com>
Carry forward bounded literal include/includeIf configuration capabilities
and env -S/--split-string words from PRs #2858 and #2897. Charge array
copy and expansion work before allocation to preserve the shared quota.
Verified 731 hook cases and 60 real Git/config and registered-route
controls. Dynamic remainder and original full source PRs remain held.
Co-authored-by: Nguyen Thanh Dat <ntdat812.dev@gmail.com>
Co-authored-by: Davemaina1 <dmain7015@gmail.com>
Resolve six conflicts:
- hooks/hooks.metadata.json: keep this branch's gateguard description and
fingerprint, add upstream's hookify-runtime entries.
- package.json: keep both gateguard-report.js and github-coordination.js.
- scripts/hooks/gateguard-fact-force.js, tests/hooks/gateguard-fact-force.test.js,
skills/gateguard/SKILL.md: upstream added a simpler session denial cap; this
branch already has the fuller one (cap threaded through
markCheckedAndCountDenial, malformed-value warning, miss and target notes),
so keep it. Upstream's taskset and su wrapper handling, fail-closed
recursion limit and soft-hyphen sanitising merged cleanly and their tests pass.
- manifests/context-packs/skill-triggers@1.json: take upstream's file and
recompute registryDigest for the merged registry.
Treat non-2xx activity responses as feed errors, preserve non-Markdown Copilot agent assets, and apply the reviewed reference escape parity correction with regenerated bindings. Allow the test runner to drain piped output on its existing success or failure exit status. Validate installed workflows and bounded real Node20/24 pipe regressions.
Match the Windows missing volume-serial exception while retaining strict reported-device, inode, ownership, permission, link and snapshot checks. Add loader warning/block and race regression controls with isolated platform metadata injection.
- A build interrupted while writing the index leaves a partial file under
its digest name before the pointer exists. The next build rejects those
bytes ("content changed under its digest") and cannot repair the index.
- A skill edited after the entries are read leaves an index that still
matches the stored generation, and the next build reports that
generation stale. This pins the current behavior: the index is bound to
the generation, not to live sources.
Open with supported no-follow and nonblocking flags before relying on file metadata. Validate descriptor, pathname and rule-directory consistency before and after reading at most64KiB plus one overflow byte. Reject observed replacement, mutation, premature EOF and non-regular files, and close descriptors on every outcome.
Add12 race and I/O regressions. Keep the Hermes uppercase protected-file fixture real on case-sensitive filesystems and verify that the installed guard still permits first-time creation.
Validation: full6688 reported tests across347 files,12 race tests, full80% coverage gates, scoped Hookify coverage, installed Hookify and Hermes workflows, packed artifact lifecycle, lint, signatures and IOC.
Two first-round review findings were never addressed, and both reproduce
on the current head:
- records.require('./label'), obj?.import('./x') and obj . require('./y')
are method calls, but the call pattern's word boundary is satisfied by
the dot, so a self-contained object method fails every projection for a
file the script never loads.
- The dynamic-argument pattern allows one level of nested parentheses, so
require(path.join(__dirname, getName())) produces no dynamic warning
while require(getName()) does.
Control: a genuine require beside the member calls is still a dependency.
Review on dd14493e found four more ways the closure gate misjudges a
carrier, each reproduced against that head:
- require('./helper') resolves when only helper.cjs or helper.mjs is
planned, but Node's CommonJS search tries only .js, .json and .node.
- In `if (ok) {} /"/.test(text); require(...)` the regex after the block
is read as division and its quote swallows the require.
- `obj.\nif(x) / 2` is a method call, but the condition check only saw
the character immediately before `if`, so the division read as a regex
and swallowed a later require. Introduced by the previous fix.
- A tagged template named `from` was recorded as an import; with exact
import resolution it now fails a carrier that never loads that path.
Introduced by the previous fix.
Controls: an extensionless require still resolves to a .json file, and a
template literal passed to import() is still a dependency.
haelyra