From 9febb1bba1d0db232730e001004e0624b6ccb32f Mon Sep 17 00:00:00 2001
From: Mathias <mthbqv@gmail.com>
Date: Thu, 11 Jun 2026 08:55:33 +0200
Subject: [PATCH] fix(claudewatcher): harden secret scrubber against \b evasion
 + add JWT

A shell mangle that glued a key to a preceding word ('yes'+'sk-...') had
no word boundary, so the leading \b in the openai-sk rule failed to match
and a LiteLLM master key leaked past the scrubber into ingest (2026-06-11).

- openai-sk: drop leading \b, match sk- shape anywhere ({32,} floor keeps
  short task-/disk- words clean).
- add jwt rule for bare header.payload.sig tokens (no Bearer prefix).
- regression tests: the exact yessk- evasion, standalone sk-, bare JWT,
  plus clean-content guards for task-/disk-.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---
 ingestion/internal/claudewatcher/scrubber.go      | 11 ++++++++++-
 ingestion/internal/claudewatcher/scrubber_test.go | 10 ++++++++++
 2 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/ingestion/internal/claudewatcher/scrubber.go b/ingestion/internal/claudewatcher/scrubber.go
index c312633..575d408 100644
--- a/ingestion/internal/claudewatcher/scrubber.go
+++ b/ingestion/internal/claudewatcher/scrubber.go
@@ -38,11 +38,20 @@ var DefaultRules = []Rule{
 	// specific match name in logs.
 	{Name: "authorization-header", RE: regexp.MustCompile(`(?i)Authorization\s*:\s*[A-Za-z]+\s+\S{8,}`)},
 	{Name: "bearer-token", RE: regexp.MustCompile(`(?i)Bearer\s+[A-Za-z0-9._\-]{16,}`)},
+	// JWT (header.payload.sig), e.g. a Dex/OAuth token dumped to stdout
+	// without a "Bearer " prefix. Both header and payload base64url-encode
+	// JSON, so both segments begin with "eyJ".
+	{Name: "jwt", RE: regexp.MustCompile(`eyJ[A-Za-z0-9_\-]{8,}\.eyJ[A-Za-z0-9_\-]{8,}\.[A-Za-z0-9_\-]{8,}`)},
 	{Name: "postgres-uri-with-password", RE: regexp.MustCompile(`postgres(?:ql)?://[^:\s/]+:[^@\s/]+@`)},
 	{Name: "private-key", RE: regexp.MustCompile(`-----BEGIN[^-]*PRIVATE KEY-----`)},
 	{Name: "ssh-key", RE: regexp.MustCompile(`ssh-(?:rsa|ed25519|ecdsa)\s+[A-Za-z0-9+/=]{40,}`)},
 	{Name: "github-pat", RE: regexp.MustCompile(`\b(?:ghp|gho|ghu|ghr|gha)_[A-Za-z0-9]{30,}\b`)},
-	{Name: "openai-sk", RE: regexp.MustCompile(`\bsk-(?:proj-)?[A-Za-z0-9]{32,}\b`)},
+	// No leading \b: a shell mangle can glue the key to a preceding word
+	// ("yes"+"sk-...") which has no word boundary, and that exact case
+	// leaked a LiteLLM master key past this rule (2026-06-11). Match the
+	// sk- shape wherever it appears; the {32,} length floor keeps short
+	// "task-"/"disk-" words from tripping it.
+	{Name: "openai-sk", RE: regexp.MustCompile(`sk-(?:proj-)?[A-Za-z0-9]{32,}`)},
 	{Name: "anthropic-sk", RE: regexp.MustCompile(`\bsk-ant-[A-Za-z0-9_\-]{32,}\b`)},
 	{Name: "aws-access-key", RE: regexp.MustCompile(`\bAKIA[0-9A-Z]{16}\b`)},
 	{Name: "homelab-env-token", RE: regexp.MustCompile(`(?i)(?:_TOKEN|_PASSWORD|_API_KEY|_SECRET)\s*[:=]\s*['"]?[A-Za-z0-9._/+\-]{12,}`)},
diff --git a/ingestion/internal/claudewatcher/scrubber_test.go b/ingestion/internal/claudewatcher/scrubber_test.go
index 524114e..3a129f4 100644
--- a/ingestion/internal/claudewatcher/scrubber_test.go
+++ b/ingestion/internal/claudewatcher/scrubber_test.go
@@ -25,6 +25,13 @@ func TestScrub_PoisonedFixtures(t *testing.T) {
 		{"aws-access-key", "AWS_ACCESS_KEY_ID=AKIAIOSFODNN7EXAMPLE", "aws-access-key"},
 		{"homelab-env", "POSTGRES_PASSWORD=hunter2supersecretvalue", "homelab-env-token"},
 		{"sops-marker", "value: ENC[AES256_GCM,data:abc123def456,iv:zzz]", "sops-encrypted-marker"},
+		// Regression: a shell mangle glued the key to a preceding word
+		// ("yes"+"sk-..."), defeating the leading \b in the sk- rule and
+		// leaking a LiteLLM master key past the scrubber (2026-06-11).
+		{"sk-glued-to-word", "master key resolved: yessk-7181ca984603239d8c4819361bf33b94b9c3c07018791868", "openai-sk"},
+		{"sk-standalone-hex", "sk-7181ca984603239d8c4819361bf33b94b9c3c07018791868", "openai-sk"},
+		// Bare JWT not preceded by "Bearer" (e.g. a Dex token dumped to stdout).
+		{"jwt-bare", "token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiIxMjM0NTY3ODkwIn0.dQw4w9WgXcQabcdef", "jwt"},
 	}
 	for _, tc := range cases {
 		t.Run(tc.name, func(t *testing.T) {
@@ -43,6 +50,9 @@ func TestScrub_CleanContentPassesThrough(t *testing.T) {
 		"file at ~/.ssh/id_ed25519",
 		"the function Authorization() takes no args",
 		"comment: see API key in 1Password",
+		// loosened sk- rule must not trip on short "task-"/"disk-" words
+		"run task-build then task-test in the pipeline",
+		"mounted /dev/disk-by-id/wwn-0x5000",
 	}
 	for _, c := range cases {
 		assert.Empty(t, Scrub(c), "expected clean for %q", c)