Skip to content

GHCR unlinked-package audit #13

GHCR unlinked-package audit

GHCR unlinked-package audit #13

# Daily audit for GHCR container packages that are unlinked from a source
# repository (`repository: null` on the GHCR API).
#
# WHY THIS EXISTS
# ---------------
# When a GHCR container package is not linked to a repository, workflow
# builds in `CopilotKit/CopilotKit` get `403 Forbidden` on push to GHCR —
# the workflow's `GITHUB_TOKEN` only has package-write permissions when
# the package is linked to the actor's repo. We hit this twice in quick
# succession (`showcase-harness` caught manually after a failed deploy, and
# `showcase-pocketbase` caught by a preemptive scan). There is NO GitHub
# API to programmatically link a package to a repo — it is UI-only — so
# the only way to prevent future surprises is detect drift early via a
# scheduled audit + Slack alert.
#
# ALLOWLIST (VERIFIED_ACCESS)
# ---------------------------
# Some packages show `repository: null` on the API but have working
# Actions access because the "Manage Actions access" setting was
# configured manually in the GitHub UI. There is NO API to detect this
# setting, so we maintain an explicit allowlist of package names that
# have been verified to have Actions write access. These are excluded
# from the unlinked-package alert to avoid false positives. See the
# VERIFIED_ACCESS array in the audit step below.
#
# This workflow is the operationalization of the lesson captured in
# `feedback_ghcr_new_package_403.md`.
#
# REQUIRED SECRETS
# ----------------
# - ORG_READ_PACKAGES_PAT: a fine-grained PAT with `read:packages` scope,
# org-scoped to `CopilotKit`. The default `secrets.GITHUB_TOKEN` does
# NOT have `read:packages` for the org and cannot list org packages.
# - SLACK_WEBHOOK_GHCR_DRIFT: a CopilotKit-internal Slack incoming-webhook
# URL. Posts to whichever channel the webhook is bound to (intended:
# an internal alerts channel).
#
# If `ORG_READ_PACKAGES_PAT` is unset the workflow fails loudly — drift
# detection silently disabled is worse than no workflow at all.
# If `SLACK_WEBHOOK_GHCR_DRIFT` is unset the workflow logs a warning
# (the audit still runs) so a missing webhook does not mask drift.
#
# EXIT CODES
# ----------
# This workflow exits 0 in all non-error cases (including when drift is
# present). The Slack message IS the alert; failing the workflow on
# drift would create noisy red CI checks on a schedule.
name: GHCR unlinked-package audit
on:
schedule:
# Daily at 14:00 UTC (07:00 PT / 10:00 ET) — low-traffic window,
# well before the US workday's deploy activity.
- cron: "0 14 * * *"
workflow_dispatch: {}
permissions:
contents: read
jobs:
audit:
name: Audit org container packages for unlinked repos
# Hoist the Slack webhook into an env var so step-level `if:`
# expressions can reference it — `secrets.*` is not a valid
# named-value inside `if:` and causes a workflow startup failure.
env:
SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK_GHCR_DRIFT }}
runs-on: ubuntu-latest
timeout-minutes: 5
steps:
- name: Verify ORG_READ_PACKAGES_PAT is set
env:
PAT: ${{ secrets.ORG_READ_PACKAGES_PAT }}
run: |
if [ -z "$PAT" ]; then
echo "::error::ORG_READ_PACKAGES_PAT is not set. This workflow requires a fine-grained PAT with read:packages scope, org-scoped to CopilotKit. See the workflow header comment in .github/workflows/ghcr_unlinked_packages.yml for setup."
exit 1
fi
echo "ORG_READ_PACKAGES_PAT present."
- name: List org container packages and identify unlinked
id: audit
env:
GH_TOKEN: ${{ secrets.ORG_READ_PACKAGES_PAT }}
run: |
set -euo pipefail
# Page through all container packages in the CopilotKit org.
# `--paginate` follows Link headers; per_page=100 minimizes
# request count. `gh api` returns one JSON array per page;
# `--slurp` is unnecessary because gh concatenates pages into
# a single stream when called with `--paginate` on an array
# endpoint.
all_packages_json="$(gh api \
--paginate \
-H "Accept: application/vnd.github+json" \
"/orgs/CopilotKit/packages?package_type=container&per_page=100")"
total="$(echo "$all_packages_json" | jq 'length')"
echo "Total container packages in CopilotKit org: $total"
# Filter for packages where repository is null. Emit a compact
# JSON array of {name, visibility} objects for downstream use.
unlinked_json="$(echo "$all_packages_json" \
| jq -c '[.[] | select(.repository == null) | {name: .name, visibility: .visibility}]')"
# Packages with `repository: null` that have verified Actions access
# configured via the GitHub UI ("Manage Actions access" → CopilotKit →
# Write). These are not truly drifted — pushes work fine — but there
# is no API to detect this, so we maintain an explicit allowlist.
# To add a package here: verify in the package settings UI that
# "Manage Actions access" lists CopilotKit with Write role, then
# add the exact package name to this array.
VERIFIED_ACCESS=("showcase-pocketbase")
# Remove allowlisted packages from the unlinked set.
unlinked_json_before_filter="$unlinked_json"
if [ ${#VERIFIED_ACCESS[@]} -gt 0 ]; then
allowlist_filter=$(printf '"%s",' "${VERIFIED_ACCESS[@]}")
allowlist_filter="[${allowlist_filter%,}]"
unlinked_json="$(echo "$unlinked_json" \
| jq -c --argjson allow "$allowlist_filter" \
'[.[] | select(.name as $n | $allow | index($n) | not)]')"
fi
skipped=$(($(echo "$unlinked_json_before_filter" | jq 'length') - $(echo "$unlinked_json" | jq 'length')))
if [ "$skipped" -gt 0 ]; then
echo "Skipped $skipped package(s) with verified Actions access (allowlist)."
fi
unlinked_count="$(echo "$unlinked_json" | jq 'length')"
echo "Unlinked container packages: $unlinked_count"
# Emit outputs for the next step. Use the multiline-output
# delimiter form for the JSON array so jq output with embedded
# special chars survives intact.
{
echo "unlinked_count=$unlinked_count"
echo "unlinked_json<<EOF"
echo "$unlinked_json"
echo "EOF"
} >> "$GITHUB_OUTPUT"
if [ "$unlinked_count" = "0" ]; then
echo "::notice::No GHCR drift — all CopilotKit org container packages are linked to a repository."
else
echo "::warning::Detected $unlinked_count unlinked container package(s):"
echo "$unlinked_json" | jq -r '.[] | " - \(.name) (\(.visibility))"'
fi
- name: Build Slack payload
id: payload
if: steps.audit.outputs.unlinked_count != '0'
env:
UNLINKED_JSON: ${{ steps.audit.outputs.unlinked_json }}
UNLINKED_COUNT: ${{ steps.audit.outputs.unlinked_count }}
RUN_URL: https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}
run: |
set -euo pipefail
# Build a single `text` field with mrkdwn — keeps the payload
# compatible with both incoming-webhooks and channel webhooks.
# Each unlinked package gets a deep link to its Actions-access
# settings page, where the UI fix lives.
lines="$(echo "$UNLINKED_JSON" | jq -r '.[] | "• <https://github.com/orgs/CopilotKit/packages/container/\(.name)/settings|\(.name)> (\(.visibility))"')"
# Build message via printf — avoids heredoc indentation
# gotchas (closing delimiter must be column-0, which confuses
# YAML linters on `run: |` blocks). mrkdwn renders *bold*,
# _italic_, and <url|label> links.
nl=$'\n'
message=":warning: *GHCR drift detected* — ${UNLINKED_COUNT} container package(s) in the \`CopilotKit\` org are unlinked from a source repository.${nl}${nl}"
message="${message}${lines}${nl}${nl}"
message="${message}*UI fix (per package):* open the settings link above → *Manage Actions access* → *Add Repository* → \`CopilotKit/CopilotKit\` → *Write*.${nl}${nl}"
message="${message}_This drift breaks future workflow builds with \`403 Forbidden\` on push to GHCR. <${RUN_URL}|View audit run>_"
# Emit as a multiline output so the next step can consume it
# without re-quoting through a shell.
{
echo "text<<EOF"
echo "$message"
echo "EOF"
} >> "$GITHUB_OUTPUT"
- name: Notify Slack (drift detected)
if: steps.audit.outputs.unlinked_count != '0' && env.SLACK_WEBHOOK != ''
uses: slackapi/slack-github-action@b0fa283ad8fea605de13dc3f449259339835fc52 # v2.1.0
with:
webhook: ${{ secrets.SLACK_WEBHOOK_GHCR_DRIFT }}
webhook-type: incoming-webhook
# Wrap the dynamic message via toJSON so quotes/newlines/
# backslashes inside package names or visibility values are
# safely JSON-encoded instead of breaking the payload.
payload: |
{ "text": ${{ toJSON(steps.payload.outputs.text) }} }
- name: Log (no Slack — webhook unset)
if: steps.audit.outputs.unlinked_count != '0' && env.SLACK_WEBHOOK == ''
run: |
echo "::warning::Drift detected but SLACK_WEBHOOK_GHCR_DRIFT is not set; no Slack notification sent. See run logs above for the unlinked package list."
- name: Log (no drift)
if: steps.audit.outputs.unlinked_count == '0'
run: |
echo "No drift — exiting 0."