Skip to content
KitploitKITPLOIT
ToolsExploitsBlog
Log in
Submit
ToolsExploitsBlog
Submit

Hacking, PenTest, and Cybersecurity Tools for Your Security Arsenal!

Kitploit is a directory of hacking, cybersecurity, and pentesting tools. Discover the latest project updates to find vulnerabilities, analyze systems, automate testing, and strengthen your security.

FeedsContactPrivacy© 2026 Kitploit

Tool Directory

Categories

View all categories
Loading categories
Letta-CVE-2025-51482-RCE — Proof-of-concept exploit for CVE-2025-51482, demonstrating remote code execution via unsafe exec() usage and sandbox bypass in the Letta AI agent framework. Includes vulnerability analysis and exploitation script. | Kitploit
Tools/GitHubGitHub/kai-one001/letta-cve-2025-51482-rce
Vulnerability AnalysisCode AnalysisExploitationWeb Application ExploitationPenetration TestingRed Teaming
GitHubkai-one001/letta-cve-2025-51482-rce

Letta-CVE-2025-51482-RCE

Proof-of-concept exploit for CVE-2025-51482, demonstrating remote code execution via unsafe exec() usage and sandbox bypass in the Letta AI agent framework. Includes vulnerability analysis and exploitation script.

View Repository
1351 year agoNot yet reviewed
Share

Letta-CVE-2025-51482-RCE

Vulnerability Cause Analysis

1. Lack of Code Security Inspection

Problem: The system does not perform any security inspection on user-provided source code.

Evidence:

  • generate_execution_script method directly inserts user code into the execution script:

    code += "\n" + self.tool.source_code + "\n"
    
  • No AST analysis to detect dangerous operations (e.g., os.system, subprocess.call, eval, etc.)

  • No import restrictions or module whitelist

2. Unsafe Use of exec()

Problem: Direct use of exec() to execute user code, with the global dictionary containing environment variables.

Evidence:

globals_dict = *dict*(env) # Environment variables directly exposed to user code
exec(code_obj, globals_dict)

3. Exposure of Environment Variables

Problem: All environment variables are exposed to user code, including sensitive information.

Evidence:

env = os.environ.copy() # Copy all system environment variables
env_vars = self.sandbox_config_manager.get_sandbox_env_vars_as_dict(...)
env.update(env_vars) # Add sandbox environment variables

4. Sandbox Bypass Mechanism

Problem: The privileged_tools mechanism can be bypassed.

Evidence:

if tool_settings.e2b_api_key and not self.privileged_tools:
  # Use e2b sandbox (relatively safe)
else:
  # Use local sandbox (unsafe)

If the organization sets privileged_tools=True or does not configure an e2b API key, the system falls back to unsafe local execution.

5. Lack of Input Validation

Problem: No validation or sanitization is performed on user-supplied source code.

Evidence: The ToolRunFromSource mode accepts arbitrary strings as source code:

source_code: *str* = Field(..., *description*="The source code of the function.")

Exploitation (Python Script)

Example:
python RCE.py -u http://192.168.63.131:8283/
[+] Command executed successfully:
uid=0(root) gid=0(root) groups=0(root)
python RCE.py -u http://192.168.63.131:8283/ -c whoami
[+] Command executed successfully:
root
Download Tool

Most Popular

View all →

Discover the most used tools by our community.

  • 1

    OsintHunter

    letox4/osinthunter

    🎯 The ultimate OSINT toolkit: investigation graph, confidence scoring, alias families, map, timeline and reports. 49 modules, 400+ sites, no API keys required.

    790
  • 2

    ghostlock-app

    yukonga/ghostlock-app

    GhostLock One-Tap Execution App (CVE-2026-43499)

    508
  • 3

    ARTEX

    baarai/artex

    LLM multi-agent autonomous penetration testing platform with planner/worker agents, asset and exploration graphs, MITM traffic recording, and vulnerability retesting.

    435
  • 4

    redforge

    cybersecurity91/redforge

    Browser-side red team toolkit with 102 offline tools for recon, payload generation, credential attacks, crypto, encoding and engagement reporting.

    346
  • 5

    CyberStrikeAI

    ed1s0nz/cyberstrikeai

    The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.

    263
  • 6

    looking-glass

    anonghosty/looking-glass

    CSIRT platform that ingests Shadowserver reports into MongoDB and replays them as interactive maps, analysis, findings, advisories and executive dashboards.

    260

Explore all tools

Browse our collection of tools

View all tools →