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
CVE-2026-1337-AI-Coding-Assistant-Prompt-Injection-to-Sandbox-Escape — A prompt injection in a code‑review bot that executes AI‑generated fixes in a sandbox. The sandbox uses a blacklist to prevent dangerous commands, but a polyglot payload bypasses the filter and achieves remote code execution. | Kitploit
Tools/GitHubGitHub/george0papasotiriou/cve-2026-1337-ai-coding-assistant-prompt-injection-to-sandbox-escape
Vulnerability AnalysisCode AnalysisExploitationLearning & EducationPayload DevelopmentAI SecurityAdversarial Attack
GitHub
george0papasotiriou/cve-2026-1337-ai-coding-assistant-prompt-injection-to-sandbox-escape

CVE-2026-1337-AI-Coding-Assistant-Prompt-Injection-to-Sandbox-Escape

A prompt injection in a code‑review bot that executes AI‑generated fixes in a sandbox. The sandbox uses a blacklist to prevent dangerous commands, but a polyglot payload bypasses the filter and achieves remote code execution.

View Repository
1373 months agoNot yet reviewed

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.

    1.1k
  • 2

    ghostlock-app

    yukonga/ghostlock-app

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

    601
  • 3

    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.

    403
  • 4

    ARTEX

    baarai/artex

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

    319
  • 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.

    265
  • 6

    Aliens_eye

    arxhr007/aliens_eye

    AI powered OSINT engine to discover and map 7,700+ social media identities across the web

    263

Explore all tools

Browse our collection of tools

View all tools →
Share

CVE-2026-1337 – AI Coding Assistant Prompt Injection to RCE

Severity: Critical CVE-2026-1337

📖 Overview

A prompt injection vulnerability in an AI-powered code review bot allows an attacker to inject arbitrary shell commands by manipulating the bot’s “fix” suggestion. The sanitizer uses a simple blacklist that is bypassed using encoding tricks.

⚙️ Vulnerability Details

  • Type: Prompt Injection → Command Injection
  • Impact: Remote Code Execution (RCE) on the CI/CD runner.
  • Root Cause: The AI model blindly echoes a user‑supplied ##Fix: section. A blacklist attempts to block dangerous commands but fails against encoded payloads (base64, variable indirection).
  • Affected Software: Hypothetical “DevBot v3.1” – simulated here for educational purposes.

🧪 Exploit Demonstration

  1. Start the vulnerable service:
    python ai_code_review_bot.py
    
  2. Run the exploit bash python exploit.py
Download Tool