diff options
Diffstat (limited to 'githooks/pre-commit')
| -rwxr-xr-x | githooks/pre-commit | 41 |
1 files changed, 35 insertions, 6 deletions
diff --git a/githooks/pre-commit b/githooks/pre-commit index 909cde22..a87bedf8 100755 --- a/githooks/pre-commit +++ b/githooks/pre-commit @@ -5,15 +5,37 @@ set -u REPO_ROOT="$(git rev-parse --show-toplevel)" -cd "$REPO_ROOT" +cd "$REPO_ROOT" || exit 1 # --- 1. Secret scan --- # Patterns for common credentials. Scans only added lines in the staged diff. -SECRET_PATTERNS='(AKIA[0-9A-Z]{16}|sk-[a-zA-Z0-9_-]{20,}|-----BEGIN (RSA|DSA|EC|OPENSSH|PGP)( PRIVATE)?( KEY| KEY BLOCK)?-----|(api[_-]?key|api[_-]?secret|auth[_-]?token|secret[_-]?key|bearer[_-]?token|access[_-]?token|password)[[:space:]]*[:=][[:space:]]*["'"'"'][^"'"'"']{16,}["'"'"'])' +# +# Two passes because case-sensitivity differs. AWS keys are uppercase, sk- keys +# lowercase, PEM headers fixed, so those match case-SENSITIVELY: under -i, +# AKIA[0-9A-Z]{16} matches any mixed-case 20-char run, which random base64 in an +# embedded image blob hits ~6% of the time per 100KB and blocks real commits. +# Only the keyword=value patterns need -i. +SECRET_PATTERNS_CS='(AKIA[0-9A-Z]{16}|sk-[a-zA-Z0-9_-]{20,}|-----BEGIN (RSA|DSA|EC|OPENSSH|PGP)( PRIVATE)?( KEY| KEY BLOCK)?-----)' +SECRET_PATTERNS_CI='(api[_-]?key|api[_-]?secret|auth[_-]?token|secret[_-]?key|bearer[_-]?token|access[_-]?token|password)[[:space:]]*[:=][[:space:]]*["'"'"'][^"'"'"']{16,}["'"'"']' -secret_hits="$(git diff --cached -U0 --diff-filter=AM \ - | grep '^+' | grep -v '^+++' \ - | grep -iEn "$SECRET_PATTERNS" || true)" +# Read the diff on its own so a git failure is distinguishable from "grep +# matched nothing". Both end in a non-zero status, but only one of them means +# there is nothing to scan; piping them together and swallowing the result with +# `|| true` made a broken git look like a clean commit — the scan searched an +# empty string, found nothing, and the secret went in. +if ! staged_diff="$(git diff --cached -U0 --diff-filter=AM)"; then + echo "pre-commit: cannot read the staged diff — refusing to skip the secret scan" >&2 + exit 1 +fi + +# The greps keep their `|| true`: exiting 1 on no match is their normal result. +added_lines="$(printf '%s\n' "$staged_diff" | grep '^+' | grep -v '^+++' || true)" + +cs_hits="$(printf '%s\n' "$added_lines" | grep -nE "$SECRET_PATTERNS_CS" || true)" +ci_hits="$(printf '%s\n' "$added_lines" | grep -niE "$SECRET_PATTERNS_CI" || true)" +# awk dedupes lines both passes matched, keeping first-seen order. +secret_hits="$(printf '%s\n%s' "$cs_hits" "$ci_hits" \ + | grep -v '^[[:space:]]*$' | awk '!seen[$0]++' || true)" if [ -n "$secret_hits" ]; then echo "pre-commit: potential secret in staged changes:" >&2 @@ -25,7 +47,14 @@ if [ -n "$secret_hits" ]; then fi # --- 2. Paren check on staged .el files --- -staged_el="$(git diff --cached --name-only --diff-filter=AM | grep '\.el$' || true)" +# Same split as the secret scan above: a git failure must not read as "no files +# staged", which would skip the language check silently. +if ! staged_names="$(git diff --cached --name-only --diff-filter=AM)"; then + echo "pre-commit: cannot read the staged file list — refusing to skip the check" >&2 + exit 1 +fi + +staged_el="$(printf '%s\n' "$staged_names" | grep '\.el$' || true)" if [ -n "$staged_el" ]; then paren_fail="" |