hermes
bb071343c2
The cluster-count guard I added used `grep -c '"name"'`, which counts
LINES. The jsonpath output is a single line, so the count was 1 for a
kubeconfig with clusters and 1 for one without - which made the guard
reject every kubeconfig:
ERROR: the kubeconfig has no cluster entries.
The count is now done with `grep -o . | wc -l`, which counts occurrences
rather than lines. Tested against both cases:
- a real kubeconfig with a stale CA -> the CA is refreshed and kubectl works
- a kubeconfig with no clusters -> refuses with a clear message
127 lines
4.8 KiB
Bash
Executable File
127 lines
4.8 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
#
|
|
# Make sure kubectl can talk to the cluster API server.
|
|
#
|
|
# The kubeconfig embeds the k3s server CA. If the cluster's CA has been
|
|
# rotated since the secret was created, kubectl fails with:
|
|
#
|
|
# tls: failed to verify certificate: x509: certificate signed by unknown authority
|
|
#
|
|
# which reads like a network problem rather than a stale secret. This script
|
|
# refreshes the CA in place.
|
|
#
|
|
# The refresh is PINNED: the server's CA is fetched over an unverified
|
|
# connection, but it is only used if its SHA-256 fingerprint matches the value
|
|
# pinned in scripts/cluster-ca.sha256. An attacker able to intercept the
|
|
# fetch cannot use it - their CA will not hash to the pinned fingerprint.
|
|
# The runner has cluster-admin credentials, so trusting an unverified CA here
|
|
# would be a privilege-escalation hole.
|
|
#
|
|
# The fingerprint is a PUBLIC value - it can be read straight off the
|
|
# certificate - so it lives in the repo rather than in a secret. That way a
|
|
# change to it is a reviewable commit, and nobody with secret-write access
|
|
# can silently repoint the CI runner at a different CA.
|
|
#
|
|
# The expected fingerprint is read from scripts/cluster-ca.sha256 next to
|
|
# this script. It can be overridden with the first argument.
|
|
#
|
|
# Usage:
|
|
# kube-ca-refresh.sh [expected-fingerprint]
|
|
#
|
|
# Exit codes:
|
|
# 0 the cluster is reachable
|
|
# 1 the cluster is not reachable and could not be fixed safely
|
|
|
|
set -euo pipefail
|
|
|
|
SCRIPT_DIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
|
|
EXPECTED="${1:-}"
|
|
if [ -z "$EXPECTED" ] && [ -f "$SCRIPT_DIR/cluster-ca.sha256" ]; then
|
|
# The file may carry comments; take the last non-comment line.
|
|
EXPECTED=$(grep -vE '^[[:space:]]*(#|$)' "$SCRIPT_DIR/cluster-ca.sha256" | tail -1 | tr -d '[:space:]')
|
|
fi
|
|
|
|
if kubectl version --request-timeout=15s >/dev/null 2>&1; then
|
|
echo "cluster reachable"
|
|
exit 0
|
|
fi
|
|
|
|
if [ -z "$EXPECTED" ]; then
|
|
echo "ERROR: the kubeconfig cannot verify the API server, and no expected CA" >&2
|
|
echo " fingerprint was supplied, so the CA cannot be refreshed safely." >&2
|
|
echo " and no pinned CA fingerprint could be found." >&2
|
|
echo " Set one in scripts/cluster-ca.sha256:" >&2
|
|
echo " openssl x509 -in server-ca.crt -noout -fingerprint -sha256" >&2
|
|
exit 1
|
|
fi
|
|
|
|
# Guard against a kubeconfig with no clusters, or an empty one.
|
|
# `grep -c` counts LINES, and the jsonpath output is a single line, so the
|
|
# count is done with grep -o and wc -l instead.
|
|
CLUSTER_COUNT=$(kubectl config view --raw -o jsonpath='{.clusters[*].name}' 2>/dev/null \
|
|
| grep -o . | wc -l || true)
|
|
if [ "${CLUSTER_COUNT:-0}" -eq 0 ]; then
|
|
echo "ERROR: the kubeconfig has no cluster entries." >&2
|
|
echo " The KUBEC_CONFIG_BUILDX_NEW_2 secret looks wrong or empty." >&2
|
|
exit 1
|
|
fi
|
|
|
|
SERVER=$(kubectl config view --raw -o jsonpath='{.clusters[0].cluster.server}')
|
|
# The cluster entry's NAME - patching the CA into a *new* entry named
|
|
# "default" would leave the original entry (and its stale CA) in use.
|
|
CLUSTER_NAME=$(kubectl config view --raw -o jsonpath='{.clusters[0].name}')
|
|
|
|
if [ -z "$SERVER" ] || [ -z "$CLUSTER_NAME" ]; then
|
|
echo "ERROR: could not read the server or cluster name from the kubeconfig." >&2
|
|
exit 1
|
|
fi
|
|
|
|
echo "server: $SERVER cluster entry: $CLUSTER_NAME"
|
|
|
|
CA_FILE=$(mktemp)
|
|
trap 'rm -f "$CA_FILE"' EXIT
|
|
|
|
# Timeouts so an unreachable API server fails the job rather than hanging
|
|
# the runner indefinitely.
|
|
curl -sk --connect-timeout 10 --max-time 30 "$SERVER/cacerts" -o "$CA_FILE"
|
|
if [ ! -s "$CA_FILE" ]; then
|
|
echo "ERROR: could not fetch the cluster CA from $SERVER/cacerts" >&2
|
|
exit 1
|
|
fi
|
|
|
|
# Normalise both to lowercase hex without separators, so the comparison does
|
|
# not depend on the colon-separated format openssl prints.
|
|
normalise() {
|
|
tr -d ':' | tr '[:upper:]' '[:lower:]'
|
|
}
|
|
|
|
ACTUAL=$(openssl x509 -in "$CA_FILE" -noout -fingerprint -sha256 | cut -d= -f2 | normalise)
|
|
WANTED=$(printf '%s' "$EXPECTED" | normalise)
|
|
|
|
echo "expected CA fingerprint: $WANTED"
|
|
echo "actual CA fingerprint: $ACTUAL"
|
|
|
|
if [ "$ACTUAL" != "$WANTED" ]; then
|
|
echo "ERROR: the cluster CA does not match the pinned fingerprint." >&2
|
|
echo " expected: $WANTED" >&2
|
|
echo " actual: $ACTUAL" >&2
|
|
echo " Refusing to use it. Either the CA has been rotated and the" >&2
|
|
echo " pinned fingerprint needs updating, or the connection was" >&2
|
|
echo " intercepted." >&2
|
|
exit 1
|
|
fi
|
|
|
|
# The fingerprint matches the pinned value, so this is the CA we expect.
|
|
kubectl config set-cluster "$CLUSTER_NAME" \
|
|
--embed-certs=true \
|
|
--certificate-authority="$CA_FILE" >/dev/null
|
|
|
|
if kubectl version --request-timeout=15s >/dev/null 2>&1; then
|
|
echo "cluster reachable after refreshing the CA"
|
|
exit 0
|
|
fi
|
|
|
|
echo "ERROR: cannot reach the cluster API server even with a refreshed CA." >&2
|
|
echo " The kubeconfig secret may be stale or invalid." >&2
|
|
exit 1
|