diff --git a/.github/workflows/public-repo-guard.yml b/.github/workflows/public-repo-guard.yml index 719718a..596b8a4 100644 --- a/.github/workflows/public-repo-guard.yml +++ b/.github/workflows/public-repo-guard.yml @@ -13,10 +13,14 @@ name: public-repo-guard # wave-av/.github must not be able to alter another repo's secret scanner). The # gitleaks binary is version-pinned AND SHA-256-verified before it runs. # -# To install on a new repo, copy all three files together: +# To install on a new repo, copy all five files together (the workflow executes +# every one of them; omit the test file and the required check fails on its +# self-test step on every push): # .github/workflows/public-repo-guard.yml # .gitleaks.toml # scripts/public-repo-guard/content-policy.sh +# scripts/public-repo-guard/body-policy.sh +# scripts/public-repo-guard/tests/body-policy.test.sh # # Scan scope: the published working TREE (gitleaks --no-git), NOT git history. The # goal is "what is public right now is clean", so a shallow checkout is sufficient. @@ -25,24 +29,53 @@ name: public-repo-guard # path glob to a repo-root `.guardignore`, or extend the repo-local `.gitleaks.toml`. on: + # `edited` matters as much as `opened`: a body can be made to leak long after the + # PR is first raised, and until this workflow covered it, nothing ever re-scanned. pull_request: + types: [opened, edited, reopened, synchronize] + issues: + types: [opened, edited] + issue_comment: + types: [created, edited] push: branches: [main, master] workflow_dispatch: +# `pull_request`, deliberately NOT `pull_request_target`: a fork PR must never get +# a write token or repo secrets just because a gate wanted to read its body. permissions: contents: read -concurrency: - group: public-repo-guard-${{ github.ref }} - cancel-in-progress: true +# Concurrency is per JOB, not per workflow: the two jobs want opposite behaviour. +# A workflow-level group would force one policy on both, and it showed: rapid body +# edits cancelled the tree job over and over, and every cancelled check-run stays +# attached to the commit, so the PR reported UNSTABLE while the live runs were green. jobs: guard: name: Secrets + content policy + # Skips issue/comment events (the tree scan has nothing to say about a comment, + # and the org should not pay for a gitleaks run every time anyone posts one). + # On pull_request it runs on EVERY action, `edited` included, and always runs + # the FULL scan. This job publishes the one check name branch protection + # requires, and GitHub evaluates a required check from the LATEST check run + # of that name on the commit: a partial (body-only) run would overwrite a red + # tree verdict with a green one, letting a body edit launder a failing secret + # scan. Re-scanning an unchanged tree on an edit is the price of a verdict + # that cannot be overwritten by a narrower one. + if: >- + github.event_name == 'pull_request' + || github.event_name == 'push' + || github.event_name == 'workflow_dispatch' + concurrency: + # cancel-in-progress is safe here BECAUSE every run of this job has + # identical full scope: whatever a superseded run would have said, its + # replacement re-checks in full. Nothing is left unscanned by a cancel. + group: public-repo-guard-tree-${{ github.event.pull_request.number || github.ref }} + cancel-in-progress: true runs-on: ubuntu-latest steps: - - uses: actions/checkout@93cb6efe18208431cddfb8368fd83d5badbf9bfd # v5.0.1 + - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1 # gitleaks' GitHub Action requires a paid license for organizations; the CLI # itself is MIT-licensed and free. Pin the version AND verify the release @@ -71,3 +104,111 @@ jobs: env: GUARD_PRIVATE_REPOS: ${{ vars.GUARD_PRIVATE_REPOS }} run: bash scripts/public-repo-guard/content-policy.sh . + + # The body gate's own fixtures. Its negatives are the load-bearing half — a + # leak gate that blocks legitimate cross-repo references gets switched off, + # and then it protects nothing. Runs here so a regression is caught by CI + # rather than by a leak. + - name: body policy self-test (fixtures) + run: bash scripts/public-repo-guard/tests/body-policy.test.sh + + # A PR body is merge-blocking, so it is scanned HERE, inside the one check + # name branch protection requires. Scanning it only in a differently named + # job would let a body edit hide behind this check's stale green result. + # Same handling discipline as body-guard below: the untrusted text goes + # payload file to scratch file, never through a run: block or an env var. + - name: Materialize the untrusted PR title/body to a file + if: github.event_name == 'pull_request' + run: | + set -euo pipefail + mkdir -p "$RUNNER_TEMP/bodyscan" + # An UNRECOGNIZED payload shape must fail, never quietly scan nothing + # and report a pass. + if [ "$(jq -r 'has("pull_request")' "$GITHUB_EVENT_PATH")" != "true" ]; then + echo "::error title=public-repo-guard (guard)::Event payload contains no pull_request object; refusing to report a pass on an unscanned body." + exit 1 + fi + jq -r '[.pull_request.title, .pull_request.body] + | map(select(. != null)) | join("\n")' \ + "$GITHUB_EVENT_PATH" > "$RUNNER_TEMP/bodyscan/body.txt" + echo "scanning $(wc -l < "$RUNNER_TEMP/bodyscan/body.txt") line(s) of body text" + + - name: body policy (PR title/body, merge-blocking) + if: github.event_name == 'pull_request' + env: + GUARD_PRIVATE_REPOS: ${{ vars.GUARD_PRIVATE_REPOS }} + run: bash scripts/public-repo-guard/body-policy.sh "$RUNNER_TEMP/bodyscan/body.txt" + + # The other half of a public repo's surface. `guard` above scans the published + # TREE and (on PRs) the merge-blocking title/body; an issue or comment BODY is + # just as world-readable and, until this job, was scanned by nothing + # server-side. That gap was real, not theoretical: a PR was blocked for naming + # a private repo in wrangler.toml while the very same name, with more + # operational detail attached, sat unchallenged in its body. + # + # Honest about what it can and cannot do. Issue and comment text is already + # public the moment it posts, so this is detection — it tells us to go redact, + # fast. Only the client-side pre-write hook can stop that class before + # publication. PR bodies are NOT scanned here: they are merge-blocking, so + # they belong to `guard`, the check name branch protection actually requires. + body-guard: + name: Body content policy + if: github.event_name == 'issues' || github.event_name == 'issue_comment' + concurrency: + # Keyed on the specific comment / issue rather than github.ref, because + # issue events all report the default branch and a ref-keyed group would let + # two comments cancel each other, leaving one unscanned. + # + # cancel-in-progress is deliberately FALSE. Every version of a body deserves a + # verdict, the job is seconds long, and a cancelled check-run lingers on the + # commit and makes an otherwise-green PR look broken. + group: public-repo-guard-body-${{ github.event.comment.id || github.event.issue.number || github.ref }} + cancel-in-progress: false + runs-on: ubuntu-latest + steps: + - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1 + with: + # Only the gate's own scripts are needed — no reason to pay for the whole + # tree on every comment. + sparse-checkout: scripts/public-repo-guard + sparse-checkout-cone-mode: false + + - name: Install ripgrep + run: command -v rg >/dev/null || (sudo apt-get update -qq && sudo apt-get install -y -qq ripgrep) + + # The body is read straight out of the event payload FILE and written to + # another file. It is never interpolated into a run: block and never placed + # in an environment variable, so shell metacharacters in a hostile body + # have nothing to act on. jq is preinstalled on the GitHub-hosted images. + - name: Materialize the untrusted title/body to a file + run: | + set -euo pipefail + mkdir -p "$RUNNER_TEMP/bodyscan" + # An UNRECOGNIZED payload shape must fail, never quietly scan nothing and + # report a pass. If the event schema ever moves, this job must go red + # rather than become a green rubber stamp over an unscanned body. + if [ "$(jq -r 'has("issue") or has("comment")' "$GITHUB_EVENT_PATH")" != "true" ]; then + echo "::error title=public-repo-guard (body-guard)::Event payload contains no issue/comment object; refusing to report a pass on an unscanned body." + exit 1 + fi + # Scan only the text THIS event delivered. On issue_comment the + # payload's .issue is the surrounding issue (or PULL REQUEST, whose + # .issue.title/.issue.body are the PR's own description), so scanning + # .issue.* on comment events would re-scan a PR body on every comment + # (duplicating the merge-blocking scan in `guard`) and, because + # issue/comment events run against the DEFAULT branch head, pin any + # failure to main rather than the PR. Nothing is left unscanned by + # the narrowing: every comment gets its own created/edited event, and + # issue bodies get theirs via issues opened/edited. + jq -r 'if has("comment") + then [.comment.body] + else [.issue.title, .issue.body] + end + | map(select(. != null)) | join("\n")' \ + "$GITHUB_EVENT_PATH" > "$RUNNER_TEMP/bodyscan/body.txt" + echo "scanning $(wc -l < "$RUNNER_TEMP/bodyscan/body.txt") line(s) of body text" + + - name: body policy (issue / comment text) + env: + GUARD_PRIVATE_REPOS: ${{ vars.GUARD_PRIVATE_REPOS }} + run: bash scripts/public-repo-guard/body-policy.sh "$RUNNER_TEMP/bodyscan/body.txt" diff --git a/scripts/public-repo-guard/body-policy.sh b/scripts/public-repo-guard/body-policy.sh new file mode 100755 index 0000000..76c1509 --- /dev/null +++ b/scripts/public-repo-guard/body-policy.sh @@ -0,0 +1,185 @@ +#!/usr/bin/env bash +# WAVE public-repo BODY policy — the internal-leak gate for PR/issue/comment text. +# +# Companion to content-policy.sh. That script scans the published working TREE; +# this one scans the other half of a public repo's surface: pull-request titles +# and bodies, issue bodies, and comment bodies. Those are equally world-readable +# and, until this script existed, were scanned by NOTHING server-side. That gap +# was not theoretical — a PR was merged whose wrangler.toml was correctly BLOCKED +# for naming a private repo while the PR body named the same repo, with more +# operational detail attached, and sailed through. +# +# Usage: scripts/public-repo-guard/body-policy.sh +# holds the untrusted text, already materialized to disk. It is passed as +# a PATH and only ever read — the body is never interpolated into a command line +# or an environment variable, so no amount of shell metacharacters in a PR body +# can influence what runs here. +# +# Exit: 0 clean · 1 blocking violation · 2 scanner error (fail closed). +# +# Allowlisting: a line carrying `guard:allow ` is exempt (an accidental +# leak never carries the marker; a deliberate one is visible in a public diff), as +# is any line matching the ABOUT-THE-CONTROL allowlist below. +set -uo pipefail + +FILE="${1:-}" +[[ -n "$FILE" && -f "$FILE" ]] || { echo "::error::body-policy: usage: body-policy.sh "; exit 2; } +command -v rg >/dev/null 2>&1 || { echo "::error::body-policy: ripgrep (rg) required"; exit 2; } + +VIOLATIONS=0 + +# Lines that TALK ABOUT the control rather than leaking through it. Without this, +# the gate blocks its own pull requests and every security discussion — the +# self-referential trap that gets a gate switched off. Ported verbatim in intent +# from the client-side gate's allowlist, which was built for exactly this. +# +# Applied ONLY to the internal-marker rule (see check() below). Every other +# rule matches content that leaks regardless of what the sentence is about: a +# credential, an IP, a path, or a private repo wired to operational detail is +# re-published even when the line quotes it to DISCUSS the gate, exactly like +# the redacted annotations below never echo a hit. For those rules, +# `guard:allow ` stays the one visible escape. +ABOUT_THE_CONTROL='(public-repo-guard|body-policy|content-policy|public-github-write-gate|\bNDA\s+(gate|guard|policy|denylist|sweep|scan|hook)\b|\bno\s+NDA\b|responsib\w*\s+disclos|SECURITY\.md)' + +# check +check() { + local sev="$1" name="$2" re="$3" why="$4" + [[ -z "$re" ]] && { echo "::error::body-policy: internal bug — empty regex for rule '$name'"; exit 2; } + # rg exit: 0=match, 1=no match, >=2=real error → FAIL CLOSED. A gate that passes + # because its scanner broke is worse than no gate: it reports success. + local raw rc + raw="$(rg -nP --no-filename -- "$re" "$FILE" 2>/dev/null)"; rc=$? + if (( rc >= 2 )); then + echo "::error title=public-repo-guard ($name)::ripgrep failed (exit $rc) scanning rule '$name' — failing closed." + exit 2 + fi + (( rc == 1 )) && return 0 + # Filter with rg, not grep: BSD/macOS grep has no -P, so a `grep -P` allowlist + # silently errors out locally while working on GNU/CI — the gate would then + # disagree with itself depending on where it ran. rg is already required above. + # + # Each stage's exit code is checked EXPLICITLY: 1 (nothing survived the filter) + # is a normal clean result, but >=2 is a broken filter and must fail closed, + # exactly like the scan above. A bare `|| true` here would turn a filter crash + # into an empty match set: a false pass from the one stage meant to narrow, + # never erase, the raw hits. + local filtered matches frc + filtered="$(printf '%s' "$raw" | rg -vN -- 'guard:allow[[:space:]]+[^[:space:]]')"; frc=$? + if (( frc >= 2 )); then + echo "::error title=public-repo-guard ($name)::ripgrep failed (exit $frc) applying the guard:allow filter for rule '$name'; failing closed." + exit 2 + fi + # The about-the-control exemption applies to internal-marker ONLY. That rule + # matches PHRASES, so a line discussing the gate trips it without leaking + # anything. Every other rule (credentials, IPs, paths, and the private-repo + # wiring-topology rule this file exists for) matches content whose mere + # presence is the leak; "body-policy would flag X bound on " + # publishes the topology just as surely as stating it outright. + case "$name" in + internal-marker) + matches="$(printf '%s' "$filtered" | rg -vNiP -- "$ABOUT_THE_CONTROL")"; frc=$? + if (( frc >= 2 )); then + echo "::error title=public-repo-guard ($name)::ripgrep failed (exit $frc) applying the about-the-control filter for rule '$name'; failing closed." + exit 2 + fi + ;; + *) matches="$filtered" ;; + esac + [[ -z "$matches" ]] && return 0 + local count; count="$(printf '%s\n' "$matches" | grep -c '')" + # Print the LINE NUMBER only — never the matched text. This annotation is itself + # world-readable, so echoing the hit would re-publish the very thing we caught. + echo "::group::[$sev] $name — $why" + printf '%s\n' "$matches" | sed -E 's/^([0-9]+):.*/ line \1: «match redacted — view the body to see it»/' + echo "::endgroup::" + if [[ "$sev" == "BLOCK" ]]; then + echo "::error title=public-repo-guard ($name)::$why — $count occurrence(s) in the title/body. Edit the body to remove it, then re-run." + VIOLATIONS=$((VIOLATIONS+1)) + else + echo "::warning title=public-repo-guard ($name)::$why — $count occurrence(s) (non-blocking; review)." + fi +} + +# --- Credential formats — never legitimate in prose -------------------------- +check BLOCK stripe-live-key '(sk|rk)_live_[A-Za-z0-9]{16,}' 'Live Stripe secret/restricted key' +check BLOCK stripe-account 'acct_[A-Za-z0-9]{16,}' 'Live Stripe account ID — financial infra, never publish' +check BLOCK anthropic-key 'sk-ant-(api|admin)[0-9]{2}-[A-Za-z0-9_-]{20,}' 'Real Anthropic API/admin key' +check BLOCK github-pat 'github_pat_[A-Za-z0-9_]{30,}' 'GitHub fine-grained PAT' +check BLOCK supabase-pat 'sbp_[a-f0-9]{40}' 'Supabase personal access token' +check BLOCK aws-akid 'AKIA[0-9A-Z]{16}' 'AWS access key ID' +check BLOCK private-key '-----BEGIN [A-Z ]*PRIVATE KEY-----' 'Embedded private key material' + +# --- Infrastructure identifiers ---------------------------------------------- +# shellcheck disable=SC2016 # $CLOUDFLARE_ACCOUNT_ID is literal guidance text +check BLOCK cf-account-id 'account_id\s*[:=]\s*["'"'"']?[0-9a-f]{32}' 'Hardcoded Cloudflare account_id — reference the env var instead' +check BLOCK internal-ip '100\.(6[4-9]|[7-9][0-9]|1[01][0-9]|12[0-7])\.[0-9]{1,3}\.[0-9]{1,3}' 'Internal Tailscale-CGNAT IP (100.64.0.0/10) — internal fleet address' +# WARN, not BLOCK: a deliberate divergence from the FILE profile, for the same +# reason private-repo-ops diverges below. In a checked-in file an operator home +# path is AUTHORED content and blocking is right; in a body it is almost always +# pasted terminal output from a repro, and a gate that makes a reporter rewrite +# a stack trace (or sprinkle guard:allow) just to file a bug gets switched off. +# The hit is still annotated: a username is worth redacting, not worth blocking +# a merge over. +# shellcheck disable=SC2016 # $HOME is literal guidance text +check WARN abs-user-path '/(Users|home)/(?!runner/)[a-z][a-z0-9._-]+/' 'Operator absolute home path — leaks identity and local layout' + +# --- Self-identified internal material --------------------------------------- +# USE vs MENTION. A body that SAYS "internal-only" is leaking; a body that QUOTES +# the phrase is describing a policy — including this one. The lookarounds exempt a +# marker wrapped in straight, smart, or backtick quotes. +# +# Not hypothetical: the first run of this job failed on its own pull request, +# because a review bot had edited the PR body to summarize the change and its +# summary quoted the phrase verbatim. The line-level allowlist could not help — +# that line named no gate. Only use-vs-mention separates the two. +# +# A quoted marker is also a trivial bypass, and that is an accepted trade. The +# threat here is the ACCIDENTAL paste; a deliberate evader has easier routes, and +# `guard:allow ` already exists as the honest, visible one. +check BLOCK internal-marker '(?i)(?#260"). A gate that fires on all of +# those gets switched off, and then it protects nothing. +# +# So a bare mention stays silent. What fires is a private repo name within ~140 +# characters of INTERNAL OPERATIONAL DETAIL — a SCREAMING_CASE credential NAME, a +# secret-binding verb, a service binding, or a secret COUNT. That is the topology +# of what is wired to what, and it is the shape that actually leaked. +# +# Names are NOT hardcoded (this file is public); CI injects them via the +# GUARD_PRIVATE_REPOS variable. Unset locally → this check is skipped. +if [[ -n "${GUARD_PRIVATE_REPOS:-}" ]]; then + # Case sensitivity is SCOPED, not global. The credential-name class stays + # case-SENSITIVE (SCREAMING_CASE is the signal; a global (?i) would make + # everyday lowercase identifiers like api_key or cache_key count as + # operational detail and block ordinary cross-repo PRs), while the prose + # alternatives and the repo names themselves match case-insensitively via + # inline (?i:...) groups. The class also allows underscores so multi-segment + # names (WAVE_VIEWPORT_LEASE_SECRET) match from their leading \b. + OPS_DETAIL='(?:[A-Z][A-Z0-9_]*_(?:SECRET|TOKEN|KEY|PASSWORD)|(?i:wrangler\s+secret|secret\s+(?:is\s+)?(?:bound|binding|list)|(?:is\s+)?bound\s+on|service\s+binding|\d{2,}\s+secrets))' + _ALT='' + IFS=', ' read -r -a _PRIV <<< "$GUARD_PRIVATE_REPOS" + for _name in "${_PRIV[@]}"; do + [[ -z "$_name" ]] && continue + # Regex-escape so metacharacters in a name match literally. + _esc="$(printf '%s' "$_name" | sed -E 's/[][(){}.^$*+?|\\]/\\&/g')" + _ALT="${_ALT:+$_ALT|}${_esc}" + done + if [[ -n "$_ALT" ]]; then + # Both orders: name-then-detail and detail-then-name. + check BLOCK private-repo-ops \ + "(?i:\\b(?:${_ALT})\\b)[^\\n]{0,140}?\\b${OPS_DETAIL}|${OPS_DETAIL}[^\\n]{0,140}?(?i:\\b(?:${_ALT})\\b)" \ + 'A private WAVE repo named alongside internal operational detail (credential name, secret binding, or secret count) — the wiring topology is not public' + fi +fi + +if (( VIOLATIONS > 0 )); then + echo "::error::public-repo-guard: $VIOLATIONS blocking body-policy violation(s) — see annotations above." + exit 1 +fi +echo "public-repo-guard: body policy OK" diff --git a/scripts/public-repo-guard/tests/body-policy.test.sh b/scripts/public-repo-guard/tests/body-policy.test.sh new file mode 100755 index 0000000..06edb2e --- /dev/null +++ b/scripts/public-repo-guard/tests/body-policy.test.sh @@ -0,0 +1,152 @@ +#!/usr/bin/env bash +# Fixture tests for body-policy.sh. +# +# Deliberately fixture-only: the gate is NEVER proved by writing a real leak into a +# live public PR body, because doing so would publish the exact thing it guards. +# +# The negatives here are the load-bearing half. A leak gate that blocks everything +# is trivially "correct" and useless — it gets disabled within a week. The bare +# cross-reference case below is the one that keeps this gate deployable. +set -uo pipefail + +SCRIPT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)/body-policy.sh" +TMP="$(mktemp -d)" +trap 'rm -rf "$TMP"' EXIT + +# The names the real gate is configured with come from an org variable; the tests +# pin their own so they are hermetic and do not depend on CI configuration. +# +# Every name below is INVENTED. This file is public and sits inside +# scripts/public-repo-guard/, which the tree scan and gitleaks deliberately +# exclude (the gate cannot scan its own fixtures without blocking itself), so a +# REAL private repo name or credential name written here would be published with +# no check standing in its way. Keep the names obviously fictional. +export GUARD_PRIVATE_REPOS="example-private-alpha, example-private-beta, example-private-gamma" + +PASS=0; FAIL=0 + +# expect +expect() { + local want="$1" name="$2" body="$3" out rc + printf '%s\n' "$body" > "$TMP/body.txt" + out="$(bash "$SCRIPT" "$TMP/body.txt" 2>&1)"; rc=$? + if [[ "$rc" == "$want" ]]; then + PASS=$((PASS+1)); printf ' ok %s\n' "$name" + else + FAIL=$((FAIL+1)); printf ' FAIL %s — want exit %s, got %s\n%s\n' "$name" "$want" "$rc" "$out" + fi + # The annotation is world-readable; a hit must never echo the matched text. + if [[ "$rc" == 1 ]] && printf '%s' "$out" | grep -qF "$body"; then + FAIL=$((FAIL+1)); printf ' FAIL %s — LEAKED the matched text into the annotation\n' "$name" + fi +} + +echo "body-policy fixtures" + +# --- must BLOCK --------------------------------------------------------------- +expect 1 'private repo + credential name' \ + 'Flip is live: EXAMPLE_LEASE_ROTATION_SECRET is bound on example-private-alpha now.' +expect 1 'private repo + credential name, reverse order' \ + 'The EXAMPLE_JOIN_SECRET was added; example-private-beta picks it up on deploy.' +# Regression: `_` is a word character, so a `\b`-anchored class without it could +# never enter EXAMPLE_LEASE_ROTATION_SECRET past its first segment in this order. +expect 1 'private repo FIRST + multi-segment credential name' \ + 'example-private-alpha now reads EXAMPLE_LEASE_ROTATION_SECRET at boot.' +# Regression: prose detail stays case-insensitive after case scoping was fixed. +expect 1 'capitalized prose detail still blocks' \ + 'This adds a Service Binding from the worker to example-private-gamma.' +expect 1 'private repo + secret count' \ + 'example-private-alpha went from 74 secrets to 75 after this change.' +expect 1 'private repo + service binding' \ + 'This adds a service binding from the worker to example-private-gamma for settlement.' +expect 1 'internal-only marker' \ + 'Attaching the internal-only rollout plan for context.' +# Regression: the marker rule is case-insensitive — the most natural phrasing of +# a not-for-public warning starts a sentence with a capital. +expect 1 'sentence-initial capitalized marker' \ + 'Do not share this rollout doc outside the team.' +# Assembled at run time rather than written as a literal: a fixture that LOOKS like +# a live AWS key trips this repo's own pre-commit secret scanners (it did, on the +# first draft). Splitting the prefix keeps the fixture exercising the real regex +# without parking a credential-shaped string in source. +AKID_FIXTURE="AKI""A1234567890ABCDEF" +expect 1 'AWS access key id' \ + "The failing job had ${AKID_FIXTURE} configured." +# Regression: the about-the-control exemption is internal-marker-only. A +# credential or wiring topology is a leak even on a line that names the gate: +# quoting a hit to discuss it re-publishes it. +expect 1 'credential on a line that also names the control' \ + "public-repo-guard already flagged ${AKID_FIXTURE} once; reposting for context." +expect 1 'topology on a line that names the control' \ + 'body-policy should have flagged EXAMPLE_SECRET bound on example-private-alpha here.' +expect 1 'internal tailscale IP' \ + 'It resolves to 100.71.4.19 from inside the fleet.' + +# --- must PASS (precision — these keep the gate deployable) ------------------- +expect 0 'bare private-repo cross-reference' \ + 'This is the companion change to example-private-beta#260; merge that one first.' +expect 0 'two private repos, no operational detail' \ + 'Both example-private-alpha and example-private-beta will need a follow-up for this.' +expect 0 'credential NAME with no private repo nearby' \ + 'The handler now reads SOME_API_TOKEN from the environment instead of a literal.' +# Regression: case sensitivity is scoped. Lowercase identifiers are everyday +# code words, not SCREAMING_CASE credential names; a global (?i) blocked these. +expect 0 'lowercase api_key near a private repo' \ + 'Companion to example-private-beta#260; fixes the api_key parsing.' +expect 0 'lowercase cache_key rename in a private repo' \ + 'example-private-alpha: rename cache_key to slot_key.' +# WARN for bodies, not BLOCK: pasted repro output routinely carries local home +# paths, and forcing a reporter to rewrite a stack trace to file a bug is the +# friction that gets a gate switched off. The divergence from the file gate is +# deliberate; see the rule's comment in body-policy.sh. +expect 0 'operator home path warns without blocking' \ + 'Repro: run it from /Users/someoperator/Documents/notes and it fails.' # enforce-ignore (fixture) +# The demotion must never quietly become deletion: the warning annotation still +# fires. No pipeline into `grep -q` here: under pipefail its early exit can +# SIGPIPE the producer and turn a MATCH into a spurious failure. +printf '%s\n' 'Repro: run it from /Users/someoperator/Documents/notes and it fails.' > "$TMP/body.txt" # enforce-ignore (fixture) +WARN_OUT="$(bash "$SCRIPT" "$TMP/body.txt" 2>&1)" +if [[ "$WARN_OUT" == *'warning title=public-repo-guard (abs-user-path)'* ]]; then + PASS=$((PASS+1)); printf ' ok operator home path still emits its WARN annotation\n' +else + FAIL=$((FAIL+1)); printf ' FAIL operator home path — WARN annotation for abs-user-path missing\n' +fi +expect 0 'public runner path is not an operator path' \ + 'CI checks out to /home/runner/work/repo/repo before the scan runs.' # enforce-ignore (fixture) +expect 0 'talking about the control' \ + 'body-policy blocks a private repo named next to a SECRET_TOKEN; that is intended.' +expect 0 'explicit guard:allow with a reason' \ + 'Example for the docs: example-private-alpha holds EXAMPLE_SECRET — guard:allow documented-example' +expect 0 'ordinary clean body' \ + 'Bumps the draft revision and regenerates the fixtures. No behaviour change.' +# Regression: the first CI run of this job failed on its own PR, because a review +# bot edited the body to summarize the change and quoted the marker verbatim. +expect 0 'marker MENTIONED in straight quotes is a description' \ + 'Blocks infra identifiers and markers (account_id, home paths, "internal-only" text).' +expect 0 'marker MENTIONED in a code span' \ + 'The rule matches `internal-only` and `for internal use` in body text.' +expect 0 'marker MENTIONED in smart quotes' \ + 'Blocks operator home paths and “internal-only” text.' +expect 1 'marker USED unquoted still blocks' \ + 'Attaching the internal-only rollout plan; do not share outside the team.' + +# --- fail closed -------------------------------------------------------------- +# Invoked directly, not through expect(): expect() always materializes a file, so +# it cannot reach these paths. A gate that returns "OK" when it was handed nothing +# to scan is the failure mode this whole file exists to prevent. +for case in "no argument at all::" "nonexistent path::$TMP/does-not-exist.txt"; do + name="${case%%::*}"; arg="${case##*::}" + if [[ -n "$arg" ]]; then bash "$SCRIPT" "$arg" >/dev/null 2>&1; else bash "$SCRIPT" >/dev/null 2>&1; fi + rc=$? + if [[ "$rc" == 2 ]]; then + PASS=$((PASS+1)); printf ' ok %s → exit 2 (fails closed)\n' "$name" + else + FAIL=$((FAIL+1)); printf ' FAIL %s — want exit 2, got %s\n' "$name" "$rc" + fi +done + +echo " ---" +if (( FAIL > 0 )); then + echo " $PASS passed, $FAIL FAILED"; exit 1 +fi +echo " $PASS passed, 0 failed"