From 3045cad1b20d7eab7ccab48606d0067b180e7706 Mon Sep 17 00:00:00 2001 From: Goksu Ceylan <79890826+GoCeylan@users.noreply.github.com> Date: Fri, 6 Mar 2026 09:36:16 -0500 Subject: [PATCH] address @sky5454 request to compile regex patterns in a txt file --- pkg/tools/default_deny_patterns.txt | 47 ++++++++++++++ pkg/tools/shell.go | 95 +++++++++++++---------------- pkg/tools/shell_test.go | 34 +++++++++++ 3 files changed, 122 insertions(+), 54 deletions(-) create mode 100644 pkg/tools/default_deny_patterns.txt diff --git a/pkg/tools/default_deny_patterns.txt b/pkg/tools/default_deny_patterns.txt new file mode 100644 index 000000000..a53d22776 --- /dev/null +++ b/pkg/tools/default_deny_patterns.txt @@ -0,0 +1,47 @@ +# Dangerous commands +\brm\s+-[rf]{1,2}\b +\bdel\s+/[fq]\b +\brmdir\s+/s\b +\b(format|mkfs|diskpart)\b\s +\bdd\s+if= +>\s*/dev/sd[a-z]\b +\b(shutdown|reboot|poweroff)\b +:\(\)\s*\{.*\};\s*: +\$\([^)]+\) +\$\{[^}]+\} +`[^`]+` +\|\s*sh\b +\|\s*bash\b +\|\s*/\S*(bash|sh|zsh|ksh|fish|csh|tcsh)\b +;\s*rm\s+-[rf] +&&\s*rm\s+-[rf] +\|\|\s*rm\s+-[rf] +>\s*/dev/null\s*>&?\s*\d? +<<\s*EOF +<<< +\$\(\s*cat\s+ +\$\(\s*curl\s+ +\$\(\s*wget\s+ +\$\(\s*which\s+ +\bsudo\b +\bsu\b.*-c\b +\bchmod\s+[0-7]{3,4}\b +\bchown\b +\bpkill\b +\bkillall\b +\bkill\s+-[9]\b +\bcurl\b.*\|\s*(sh|bash) +\bwget\b.*\|\s*(sh|bash) +\bnpm\s+install\s+-g\b +\bpip\s+install\s+--user\b +\bapt\s+(install|remove|purge)\b +\byum\s+(install|remove)\b +\bdnf\s+(install|remove)\b +\bdocker\s+run\b +\bdocker\s+exec\b +\bgit\s+push\b +\bgit\s+force\b +\bssh\b.*@ +\beval\b +\bsource\s+\S+ +(?:^|&&|\|\||;)\s*\.\s+\S diff --git a/pkg/tools/shell.go b/pkg/tools/shell.go index 2135f39f7..11864e9cd 100644 --- a/pkg/tools/shell.go +++ b/pkg/tools/shell.go @@ -3,6 +3,7 @@ package tools import ( "bytes" "context" + _ "embed" "errors" "fmt" "os" @@ -24,53 +25,42 @@ type ExecTool struct { restrictToWorkspace bool } -var defaultDenyPatterns = []*regexp.Regexp{ - regexp.MustCompile(`\brm\s+-[rf]{1,2}\b`), - regexp.MustCompile(`\bdel\s+/[fq]\b`), - regexp.MustCompile(`\brmdir\s+/s\b`), - regexp.MustCompile(`\b(format|mkfs|diskpart)\b\s`), // Match disk wiping commands (must be followed by space/args) - regexp.MustCompile(`\bdd\s+if=`), - regexp.MustCompile(`>\s*/dev/sd[a-z]\b`), // Block writes to disk devices (but allow /dev/null) - regexp.MustCompile(`\b(shutdown|reboot|poweroff)\b`), - regexp.MustCompile(`:\(\)\s*\{.*\};\s*:`), - regexp.MustCompile(`\$\([^)]+\)`), - regexp.MustCompile(`\$\{[^}]+\}`), - regexp.MustCompile("`[^`]+`"), - regexp.MustCompile(`\|\s*sh\b`), - regexp.MustCompile(`\|\s*bash\b`), - regexp.MustCompile(`\|\s*/\S*(bash|sh|zsh|ksh|fish|csh|tcsh)\b`), // shell by full path: | /bin/bash, | /usr/bin/sh - regexp.MustCompile(`;\s*rm\s+-[rf]`), - regexp.MustCompile(`&&\s*rm\s+-[rf]`), - regexp.MustCompile(`\|\|\s*rm\s+-[rf]`), - regexp.MustCompile(`>\s*/dev/null\s*>&?\s*\d?`), - regexp.MustCompile(`<<\s*EOF`), - regexp.MustCompile(`<<<`), // here-string: bash <<< "rm -rf /" - regexp.MustCompile(`\$\(\s*cat\s+`), - regexp.MustCompile(`\$\(\s*curl\s+`), - regexp.MustCompile(`\$\(\s*wget\s+`), - regexp.MustCompile(`\$\(\s*which\s+`), - regexp.MustCompile(`\bsudo\b`), - regexp.MustCompile(`\bsu\b.*-c\b`), // su -c / su root -c as sudo alternative - regexp.MustCompile(`\bchmod\s+[0-7]{3,4}\b`), - regexp.MustCompile(`\bchown\b`), - regexp.MustCompile(`\bpkill\b`), - regexp.MustCompile(`\bkillall\b`), - regexp.MustCompile(`\bkill\s+-[9]\b`), - regexp.MustCompile(`\bcurl\b.*\|\s*(sh|bash)`), - regexp.MustCompile(`\bwget\b.*\|\s*(sh|bash)`), - regexp.MustCompile(`\bnpm\s+install\s+-g\b`), - regexp.MustCompile(`\bpip\s+install\s+--user\b`), - regexp.MustCompile(`\bapt\s+(install|remove|purge)\b`), - regexp.MustCompile(`\byum\s+(install|remove)\b`), - regexp.MustCompile(`\bdnf\s+(install|remove)\b`), - regexp.MustCompile(`\bdocker\s+run\b`), - regexp.MustCompile(`\bdocker\s+exec\b`), - regexp.MustCompile(`\bgit\s+push\b`), - regexp.MustCompile(`\bgit\s+force\b`), - regexp.MustCompile(`\bssh\b.*@`), - regexp.MustCompile(`\beval\b`), - regexp.MustCompile(`\bsource\s+\S+`), // was: \.sh\b — now catches any sourced file - regexp.MustCompile(`(?:^|&&|\|\||;)\s*\.\s+\S`), // dot-sourcing: . evil.sh / && . evil.sh +//go:embed default_deny_patterns.txt +var defaultDenyPatternsText string + +var defaultDenyPatterns = mustCompileRegexPatterns(parsePatternLines(defaultDenyPatternsText)) + +func parsePatternLines(text string) []string { + lines := strings.Split(text, "\n") + patterns := make([]string, 0, len(lines)) + for _, line := range lines { + trimmed := strings.TrimSpace(line) + if trimmed == "" || strings.HasPrefix(trimmed, "#") { + continue + } + patterns = append(patterns, trimmed) + } + return patterns +} + +func compileRegexPatterns(patterns []string) ([]*regexp.Regexp, error) { + compiled := make([]*regexp.Regexp, 0, len(patterns)) + for _, p := range patterns { + re, err := regexp.Compile(p) + if err != nil { + return nil, fmt.Errorf("invalid pattern %q: %w", p, err) + } + compiled = append(compiled, re) + } + return compiled, nil +} + +func mustCompileRegexPatterns(patterns []string) []*regexp.Regexp { + compiled, err := compileRegexPatterns(patterns) + if err != nil { + panic("invalid default deny patterns: " + err.Error()) + } + return compiled } func NewExecTool(workingDir string, restrict bool) *ExecTool { @@ -324,13 +314,10 @@ func (t *ExecTool) SetRestrictToWorkspace(restrict bool) { } func (t *ExecTool) SetAllowPatterns(patterns []string) error { - t.allowPatterns = make([]*regexp.Regexp, 0, len(patterns)) - for _, p := range patterns { - re, err := regexp.Compile(p) - if err != nil { - return fmt.Errorf("invalid allow pattern %q: %w", p, err) - } - t.allowPatterns = append(t.allowPatterns, re) + compiled, err := compileRegexPatterns(patterns) + if err != nil { + return fmt.Errorf("invalid allow pattern: %w", err) } + t.allowPatterns = compiled return nil } diff --git a/pkg/tools/shell_test.go b/pkg/tools/shell_test.go index 1869a7e7e..d836517e2 100644 --- a/pkg/tools/shell_test.go +++ b/pkg/tools/shell_test.go @@ -320,3 +320,37 @@ func TestShellTool_RestrictToWorkspace(t *testing.T) { ) } } + +func TestParsePatternLines(t *testing.T) { + input := ` +# comment +\brm\s+-[rf]{1,2}\b + + # another comment +\bsource\s+\S+ +` + got := parsePatternLines(input) + if len(got) != 2 { + t.Fatalf("expected 2 patterns, got %d: %#v", len(got), got) + } + if got[0] != `\brm\s+-[rf]{1,2}\b` { + t.Fatalf("unexpected first pattern: %q", got[0]) + } + if got[1] != `\bsource\s+\S+` { + t.Fatalf("unexpected second pattern: %q", got[1]) + } +} + +func TestCompileRegexPatterns(t *testing.T) { + compiled, err := compileRegexPatterns([]string{`\brm\s+-[rf]{1,2}\b`, `\bsource\s+\S+`}) + if err != nil { + t.Fatalf("expected compile success, got error: %v", err) + } + if len(compiled) != 2 { + t.Fatalf("expected 2 compiled regexes, got %d", len(compiled)) + } + + if _, err := compileRegexPatterns([]string{`[`}); err == nil { + t.Fatalf("expected invalid regex error, got nil") + } +}