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
Tools/GitHubGitHub/astianjy/cve-2026-42203
Vulnerability AnalysisExploitationWeb Application ExploitationPenetration TestingLearning & EducationLabs & Practice
GitHubastianjy/cve-2026-42203

CVE-2026-42203

Proof-of-concept exploit for CVE-2026-42203, an SSTI vulnerability in LiteLLM's /prompts/test endpoint, with CEYE callback verification for authorized testing.

View Repository
206 months agoNot yet reviewed
Share

LiteLLM CVE-2026-42203 PoC Usage Instructions

This document explains how to start a local LiteLLM environment and run CVE-2026-42203.py to verify the /prompts/test SSTI vulnerability.

Only use in a local experimental environment that you are authorized to test. Do not point the script at unauthorized public targets.

1. Start the Local Environment

Navigate to the Lab directory and start LiteLLM, Postgres, and Prometheus:

docker compose up -d

Check container status:

docker compose ps

Confirm the service is accessible:

curl http://127.0.0.1:4000/

The default Master_Key is: sk-master-test-key-1234

2. Configure CEYE and LiteLLM Key

http://ceye.io/profile

Provide them via command line arguments:

python3 cve_2026_42203_litellm_prompts_test_ssti.py \
  --auth 'sk-local-test-key' \
  --ceye-domain 'your-id.ceye.io' \
  --ceye-token 'your-ceye-api-token'

Variable descriptions:

  • LITELLM_API_KEY: The LiteLLM access key. In the local Docker environment, this usually corresponds to LITELLM_MASTER_KEY in the .env file.
  • CEYE_DOMAIN: Your CEYE subdomain, e.g. xxxxxx.ceye.io.
  • CEYE_TOKEN: Your CEYE API Token, used to query callback records.

3. Execute the PoC

Full example:

python3 cve_2026_42203_litellm_prompts_test_ssti.py \
  --target http://127.0.0.1:4000 \
  --auth 'sk-local-test-key' \
  --ceye-domain 'your-id.ceye.io' \
  --ceye-token 'your-ceye-api-token'

Key parameters:

  • --target: LiteLLM service address, default is http://127.0.0.1:4000.
  • --auth / --api-key: The LiteLLM key used to call /prompts/test.
  • --ceye-domain: CEYE callback domain.
  • --ceye-token: CEYE API Token. The script will automatically mask it in output.
  • --wait: Seconds to wait for CEYE callback, default 20.
  • --interval: Seconds between polling CEYE records, default 3.
  • --timeout: HTTP request timeout, default 10 seconds.
  • --insecure: Add this parameter if the target uses a self-signed HTTPS certificate to disable TLS certificate verification.

4. Result Interpretation

If CEYE receives a callback, the script outputs:

[VULNERABLE] CEYE received the callback request.

If no callback is received within the wait window, the script outputs:

[NOT_VULNERABLE] CEYE did not receive the callback request within the wait window.
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.

    911
  • 2

    ghostlock-app

    yukonga/ghostlock-app

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

    548
  • 3

    redforge

    cybersecurity91/redforge

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

    366
  • 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.

    362
  • 5

    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.

    311
  • 6

    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.

    287

Explore all tools

Browse our collection of tools

View all tools →