hyperguild/ingestion/internal/claudewatcher/scrubber_test.go

package claudewatcher

import (
	"testing"

	"github.com/stretchr/testify/assert"
)

func TestScrub_PoisonedFixtures(t *testing.T) {
	// One representative bad-string per rule. If a rule fires for the
	// wrong content shape later, this table localises the regression.
	cases := []struct {
		name    string
		content string
		want    string
	}{
		{"bearer-token", "curl -H 'Authorization: Bearer abcdef1234567890ghijklmnop'", "authorization-header"},
		{"bearer-no-header", "header = Bearer eyJhbGciOiJIUzI1NiJ9.payload.sig", "bearer-token"},
		{"postgres-uri", "DATABASE_URL=postgres://user:s3cret@10.0.1.20:5432/brain", "postgres-uri-with-password"},
		{"private-key", "-----BEGIN OPENSSH PRIVATE KEY-----\nb3BlbnNzaC1rZXktdjEAAAAA", "private-key"},
		{"ssh-public", "deploy: ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIK1234567890abcdefghij user@host", "ssh-key"},
		{"github-pat-classic", "GH_TOKEN=ghp_aBcD1234EfGh5678IjKl9012MnOp3456QrSt", "github-pat"},
		{"openai-key", "OPENAI_API_KEY=sk-proj-AAAABBBBCCCCDDDDEEEEFFFFGGGGHHHHIIII", "openai-sk"},
		{"anthropic-key", "ANTHROPIC_API_KEY=sk-ant-api03-aaaaBBBBccccDDDDeeeeFFFFggggHHHHiiiiJJJJkkkk", "anthropic-sk"},
		{"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) {
			got := Scrub(tc.content)
			assert.Equal(t, tc.want, got)
		})
	}
}

func TestScrub_CleanContentPassesThrough(t *testing.T) {
	cases := []string{
		"",
		"plain text with no credentials",
		"a 40 char hex string aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa is fine in isolation",
		"`Bearer` token mentioned in docs without an actual value",
		"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)
	}
}

func TestScrub_FirstMatchWins(t *testing.T) {
	// Content matching multiple rules: report the first rule order in
	// DefaultRules. Stability matters for log triage.
	content := "Authorization: Bearer ghp_aBcD1234EfGh5678IjKl9012MnOp3456QrSt"
	assert.Equal(t, "authorization-header", Scrub(content))
}

func TestRegisterRule_ClientNameGuard(t *testing.T) {
	t.Cleanup(ResetExtraRules)
	require := func(err error) {
		if err != nil {
			t.Fatalf("unexpected err: %v", err)
		}
	}
	require(RegisterRule("client-name", `(?i)\b(SEB|Mastercard)\b`))

	// Hits — case variations + word-boundary respect.
	for _, hit := range []string{
		"mentioned SEB in this commit",
		"the Mastercard project deadline",
		"working on mastercard scope",
		"SEB internal review",
	} {
		assert.Equal(t, "client-name", Scrub(hit), "should match %q", hit)
	}

	// Misses — substring within a longer word should NOT match
	// thanks to \b. "Sebastian" contains "seb" but \b prevents hit.
	for _, miss := range []string{
		"Sebastian wrote the docs",
		"unrelated text",
		"researcher",
		"https://example.com/search?seb=1", // 'seb' bounded by ?=, still matches \b
	} {
		got := Scrub(miss)
		if miss == "https://example.com/search?seb=1" {
			// `seb=` has word-boundary at '='; this DOES match \bseb\b.
			// Accept either outcome; document the tradeoff.
			assert.Contains(t, []string{"", "client-name"}, got)
			continue
		}
		assert.Empty(t, got, "should NOT match %q", miss)
	}
}

func TestRegisterRule_CredentialsTakePrecedence(t *testing.T) {
	t.Cleanup(ResetExtraRules)
	require := func(err error) {
		if err != nil {
			t.Fatalf("unexpected err: %v", err)
		}
	}
	require(RegisterRule("client-name", `\b(SEB)\b`))

	// Content matches both a credential rule AND a client rule —
	// credential rule wins by ordering, so log triage points at the
	// strictly more dangerous leak.
	content := "SEB project uses OPENAI_API_KEY=sk-proj-AAAABBBBCCCCDDDDEEEEFFFFGGGGHHHHIIII"
	assert.Equal(t, "openai-sk", Scrub(content))
}

func TestRegisterRule_RejectsInvalidPattern(t *testing.T) {
	t.Cleanup(ResetExtraRules)
	err := RegisterRule("bad", "[unclosed")
	assert.Error(t, err)
}