fix(sandbox): normalize launcher names before the command-prefix denylist

internal/agent/command_prefix_test.go

@@ -99,6 +99,43 @@ func TestProposedCommandPrefixRejectsUnsafeRequestedPrefix(t *testing.T) {
 	}
 }
 
+// The launcher denylist is only worth anything if it holds on the path a user
+// actually sees. A model naming its own prefix_rule is that path: before
+// launcher names were normalized, "python3.11" was offered as a one-token
+// grant, and hasStringPrefix then matched every later python3.11 invocation.
+func TestProposedCommandPrefixRejectsLauncherSpellingsInRequestedPrefix(t *testing.T) {
+	for _, testCase := range []struct {
+		command string
+		rule    []any
+	}{
+		{"python3.11 script.py", []any{"python3.11"}},
+		{"python.exe script.py", []any{"python.exe"}},
+		{"node.exe app.js", []any{"node.exe"}},
+		{"cmd /c whoami", []any{"cmd"}},
+		{"busybox sh -c id", []any{"busybox"}},
+		{"uv run main.py", []any{"uv", "run"}},
+		{"python3.11 -c import_os", []any{"python3.11", "-c"}},
+	} {
+		got := proposedCommandPrefix("bash", map[string]any{
+			"command":     testCase.command,
+			"prefix_rule": testCase.rule,
+		})
+		if got != nil {
+			t.Errorf("prefix_rule %v for %q was offered as %#v, want rejected", testCase.rule, testCase.command, got)
+		}
+	}
+}
+
+func TestProposedCommandPrefixStillOffersOrdinaryCommands(t *testing.T) {
+	got := proposedCommandPrefix("bash", map[string]any{
+		"command":     "cargo build --release",
+		"prefix_rule": []any{"cargo", "build"},
+	})
+	if len(got) != 2 || got[0] != "cargo" || got[1] != "build" {
+		t.Fatalf("ordinary prefix rule = %#v, want [cargo build]", got)
+	}
+}
+
 func TestProposedCommandPrefixRejectsUnsafeShellForms(t *testing.T) {
 	cases := []string{
 		"cat < in > out",

internal/execution/contracts.go

@@ -9,7 +9,16 @@ import (
 	"strings"
 )
 
-const PolicyVersion = 1
+// PolicyVersion is the version of the approval policy that recorded grants were
+// evaluated under. Bump it whenever a change narrows what may be approved: the
+// grant store then backs the file up, keeps deny grants, invalidates prior
+// approvals, and tells the user once, instead of silently honoring approvals
+// that the current rules would have refused.
+//
+// v2 tightened command-prefix validation so a launcher spelled with a version
+// or an executable extension ("python3.11", "python.exe") can no longer be
+// approved as an ordinary command.
+const PolicyVersion = 2
 
 type Origin string
 

internal/sandbox/command_prefix.go

@@ -148,8 +148,10 @@ func unsafeCommandPrefix(prefix []string) bool {
 			return true
 		}
 	}
+	normalized := append([]string(nil), prefix...)
+	normalized[0] = normalizeLauncherName(normalized[0])
 	for _, banned := range bannedCommandPrefixSuggestions {
-		if sameStringSlice(prefix, banned) {
+		if sameStringSlice(prefix, banned) || sameStringSlice(normalized, banned) {
 			return true
 		}
 	}
@@ -165,25 +167,118 @@ func unsafeCommandPrefixPart(part string) bool {
 }
 
 func unsafeCommandPrefixLauncher(program string) bool {
-	program = strings.ToLower(strings.TrimSpace(program))
-	if strings.ContainsAny(program, `/\`) {
+	// A path is already refused. ":" and "~" are refused for the same reason:
+	// on Windows they introduce names that resolve to a different file than the
+	// one matched here, and no list can keep up with them. "PYTHON~1.EXE" is
+	// python.exe under an 8.3 short name, and 8.3 truncates the stem, so
+	// "POWERS~1.EXE" cannot be recognized by name at all; "python.exe::$DATA"
+	// names the same executable through its default stream. Refusing the shape
+	// costs a permission prompt on names no real command uses.
+	if strings.ContainsAny(program, `/\:~`) {
 		return true
 	}
-	switch program {
-	case "bash", "sh", "zsh", "/bin/bash", "/bin/zsh",
-		"pwsh", "powershell", "powershell.exe",
-		"env", "sudo", "doas", "su", "run0", "osascript",
+	name := normalizeLauncherName(program)
+	return bannedLauncherName(name) || bannedLauncherName(strings.TrimRight(name, "0123456789"))
+}
+
+func bannedLauncherName(name string) bool {
+	switch name {
+	case "bash", "sh", "zsh", "dash", "ash", "ksh", "csh", "tcsh", "fish", "busybox",
+		"pwsh", "powershell", "cmd", "wsl",
+		"env", "sudo", "sudoedit", "doas", "su", "run0", "osascript",
 		"command", "eval", "exec", "time",
 		"find", "xargs", "timeout", "nice", "nohup", "watch", "setsid", "stdbuf", "ionice",
-		"ssh", "make", "npm", "npx",
-		"python", "python3", "py", "pythonw", "pyw", "pypy", "pypy3",
-		"node", "perl", "ruby", "php", "lua", "deno", "bun":
+		"ssh", "make", "npm", "npx", "pnpm", "yarn", "bunx",
+		"python", "py", "pythonw", "pyw", "pypy", "uv", "uvx",
+		"node", "nodejs", "perl", "ruby", "php", "lua", "deno", "bun":
 		return true
 	default:
 		return false
 	}
 }
 
+// normalizeLauncherName reduces a program name to the launcher it actually runs
+// so the list above cannot be stepped around by spelling the same interpreter
+// differently: "python3.11", "python.exe" and "PYTHON3" all reach it as a name
+// the list matches. internal/agent's commandName already normalizes case and
+// Windows executable extensions on the allow side; this side matched raw, so
+// every versioned or .exe-suffixed launcher validated as an ordinary command
+// and persisted as a prefix grant that auto-allows every later invocation.
+//
+// A name is only ever narrowed toward an existing entry, so the failure
+// direction is an extra permission prompt, never a silent grant.
+func normalizeLauncherName(program string) string {
+	name := strings.ToLower(strings.TrimSpace(program))
+	// Windows discards trailing dots and spaces when resolving a filename, so
+	// "python." starts python.exe. Drop them before anything matches on the
+	// result, on every platform: the deny side must not depend on which OS is
+	// reading the grant, since the grants file travels with a synced home
+	// directory.
+	name = strings.TrimRight(name, ". ")
+	for _, suffix := range []string{".exe", ".cmd", ".bat", ".com", ".ps1"} {
+		if strings.HasSuffix(name, suffix) {
+			name = strings.TrimSuffix(name, suffix)
+			name = strings.TrimRight(name, ". ")
+			break
+		}
+	}
+	return trimLauncherVersion(trimLauncherABISuffix(trimLauncherBuildSuffix(name)))
+}
+
+// trimLauncherBuildSuffix drops the build-channel suffixes distributions and
+// upstreams append to an otherwise unchanged interpreter, so "python3.11-dbg",
+// "bash-static" and "pwsh-preview" are the launchers they say they are. The set
+// is closed on purpose: a general "-word" strip would also swallow
+// "node-gyp", "python3-config" and "ruby-lsp", which are ordinary tools a user
+// should still be able to approve.
+func trimLauncherBuildSuffix(name string) string {
+	for _, suffix := range []string{"-dbg", "-debug", "-static", "-nightly", "-preview", "-beta"} {
+		if strings.HasSuffix(name, suffix) {
+			return strings.TrimSuffix(name, suffix)
+		}
+	}
+	return name
+}
+
+// trimLauncherABISuffix drops CPython's ABI flags from a versioned interpreter
+// name, so "python3.7m" and "python3.6dm" reduce to their version, and the
+// free-threaded builds "python3.13t" and "python3.13td" reduce to theirs. The
+// flags are only removed when a digit sits underneath them, which leaves
+// ordinary names that happen to end in those letters alone: "sha256sum" keeps
+// its "sum", "zstd" its "td", "cat" its "t".
+func trimLauncherABISuffix(name string) string {
+	trimmed := strings.TrimRight(name, "dmut")
+	if trimmed == name || trimmed == "" {
+		return name
+	}
+	if last := trimmed[len(trimmed)-1]; last < '0' || last > '9' {
+		return name
+	}
+	return trimmed
+}
+
+// trimLauncherVersion drops a trailing "<separator><digits>" version from a
+// program name, so "python3.11" becomes "python3" and "python2.7" becomes
+// "python2". Digits without a separator are part of the name, which keeps
+// "base64", "7z" and "sha256sum" intact; the caller handles the "python3" shape
+// by also testing the digit-stripped form.
+func trimLauncherVersion(name string) string {
+	for {
+		trimmed := strings.TrimRight(name, "0123456789")
+		if trimmed == name || trimmed == "" {
+			return name
+		}
+		if !strings.HasSuffix(trimmed, ".") && !strings.HasSuffix(trimmed, "-") {
+			return name
+		}
+		next := trimmed[:len(trimmed)-1]
+		if next == "" {
+			return name
+		}
+		name = next
+	}
+}
+
 func sameStringSlice(left []string, right []string) bool {
 	if len(left) != len(right) {
 		return false

internal/sandbox/command_prefix_test.go

@@ -0,0 +1,115 @@
+package sandbox
+
+import "testing"
+
+func TestUnsafeCommandPrefixLauncherIgnoresVersionAndExtension(t *testing.T) {
+	for _, program := range []string{
+		"python3", "python", "node", "git", "sh", "bash", "sudo",
+		"python3.11", "python3.12", "python2.7", "python3.13.1",
+		"python.exe", "python3.exe", "node.exe", "git.exe", "bash.exe",
+		"PYTHON3.11", "Node.EXE",
+		"cmd", "cmd.exe", "wsl", "wsl.exe",
+		// Windows resolves these to the same executable.
+		"python.", "python3.", "python3.11.", "python.exe.", "PYTHON.",
+		"python.cmd", "python.bat", "python.com", "python.ps1",
+		"PYTHON~1.EXE", "POWERS~1.EXE", "python.exe::$DATA",
+		// Versioned and ABI-suffixed interpreters.
+		"python3.7m", "python3.6dm", "pythonw3.11", "python-3.11",
+		// Free-threaded CPython (PEP 703) ships beside the GIL build.
+		"python3.13t", "python3.13t.exe", "python3.14t", "python3.13td",
+		// Distribution and build-channel spellings of the same interpreter.
+		"nodejs", "nodejs.exe", "node-nightly", "python3-dbg", "python3.11-dbg",
+		"python3.13t-dbg", "python3-debug", "python3.11-debug", "node-beta",
+		"pwsh-preview", "bash-static", "sudoedit",
+		// Twins of npm and npx, which the list already refuses.
+		"pnpm", "yarn", "bunx", "pnpm.cmd", "yarn.exe",
+		"perl5.36", "ruby3.2", "php8", "lua5.4", "node22.exe", "bash5",
+	} {
+		if !unsafeCommandPrefix([]string{program}) {
+			t.Errorf("unsafeCommandPrefix([%q]) = false, want true", program)
+		}
+	}
+}
+
+func TestUnsafeCommandPrefixKeepsOrdinaryCommandsGrantable(t *testing.T) {
+	for _, prefix := range [][]string{
+		{"cargo", "build"},
+		{"go", "test"},
+		{"ls", "-la"},
+		{"rg", "--json"},
+		{"7z", "l"},
+		{"base64", "-d"},
+		{"kubectl", "get", "pods"},
+		{"docker", "ps"},
+		{"sha256sum", "file"},
+		{"gcc-13", "-c"},
+		{"node-gyp", "build"},
+		{"python3-config", "--includes"},
+		{"s3cmd", "ls"},
+		{"cat", "file"},
+		{"zstd", "-d"},
+		{"sqlite3", "db"},
+		{"yt-dlp", "url"},
+		{"perl-doc", "-h"},
+		{"php-fpm", "-t"},
+		{"ruby-lsp", "--version"},
+		{"lua-language-server", "--check"},
+		{"nodemon", "app.js"},
+	} {
+		if unsafeCommandPrefix(prefix) {
+			t.Errorf("unsafeCommandPrefix(%q) = true, want false", prefix)
+		}
+	}
+}
+func TestNormalizeLauncherName(t *testing.T) {
+	for _, testCase := range []struct{ in, want string }{
+		{"python3.11", "python3"},
+		{"python2.7", "python2"},
+		{"pypy3", "pypy3"},
+		{"node.exe", "node"},
+		{"POWERSHELL.EXE", "powershell"},
+		{"7z", "7z"},
+		{"base64", "base64"},
+		{"sha256sum", "sha256sum"},
+		{"python.", "python"},
+		{"python3.11.exe.", "python3"},
+		{"python3.7m", "python3"},
+		{"python3.6dm", "python3"},
+		{"python3.13t", "python3"},
+		{"python3.13td", "python3"},
+		{"python3.11-dbg", "python3"},
+		{"node-nightly", "node"},
+		{"node-gyp", "node-gyp"},
+		{"python3-config", "python3-config"},
+		{"zstd", "zstd"},
+		{"cat", "cat"},
+		{"cargo", "cargo"},
+		{"", ""},
+	} {
+		if got := normalizeLauncherName(testCase.in); got != testCase.want {
+			t.Errorf("normalizeLauncherName(%q) = %q, want %q", testCase.in, got, testCase.want)
+		}
+	}
+}
+
+// Session-scoped grants are the agent's other entry point (loop.go grants them
+// for a single turn without touching the store), so they must refuse the same
+// launcher spellings the persisted path does.
+func TestGrantCommandPrefixForSessionRefusesLauncherVariants(t *testing.T) {
+	engine := &Engine{commandPrefixes: newCommandPrefixGrantSet()}
+	engine.GrantCommandPrefixForSession("bash", []string{"cargo", "build"})
+	if _, ok := engine.LookupCommandPrefixForSession("bash", []string{"cargo", "build", "--release"}); !ok {
+		t.Fatal("CONTROL BROKEN: an ordinary session prefix grant did not match")
+	}
+	for _, prefix := range [][]string{
+		{"python3.11", "-c"},
+		{"python.exe", "-c"},
+		{"cmd", "/c"},
+	} {
+		engine.GrantCommandPrefixForSession("bash", prefix)
+		command := append(append([]string(nil), prefix...), "whatever")
+		if _, ok := engine.LookupCommandPrefixForSession("bash", command); ok {
+			t.Errorf("session grant %q matched %q, want refused", prefix, command)
+		}
+	}
+}