Skip to content
KitploitKITPLOIT
ToolsBlog
Submit
ToolsBlog
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.

··Feeds·Contact·Privacy·© 2026 Kitploit

Tool Directory

Categories

View all categories
Loading categories
CVE-2026-78906-ChatGPT-Prompt-Injection — AI Infrastructure Vulnerability Research. CVE-2026-78906: Prompt injection and memory exfiltration in OpenAI's ChatGPT API. | Kitploit
Tools/GitHubGitHub/vxssroott/cve-2026-78906-chatgpt-prompt-injection
Vulnerability AnalysisExploitationPapers & ResearchLearning & EducationAI Security
GitHubvxssroott/cve-2026-78906-chatgpt-prompt-injection

CVE-2026-78906-ChatGPT-Prompt-Injection

AI Infrastructure Vulnerability Research. CVE-2026-78906: Prompt injection and memory exfiltration in OpenAI's ChatGPT API.

View Repository
720 days agoNot yet reviewed

Most Popular

View all →

Discover the most used tools by our community.

Explore all tools

Browse our collection of tools

View all tools →
Share

CVE-2026-78906 — PromptGhost

ChatGPT API — Prompt Injection & Memory Exfiltration

FieldValue
Severity8.7 (High)
VectorNetwork
Affected VersionsAPI v1.0 – v1.3
Discovered By𝕍𝕠𝕤𝕤🥷

Description

A critical vulnerability in OpenAI's ChatGPT API allows an attacker to inject malicious prompts that bypass system‑level restrictions and exfiltrate previous conversation context.

Impact

  • Unauthorised access to conversation history
  • Exfiltration of sensitive context
  • System prompt bypass
  • Potential for data leakage

Mitigation

  • Implement strict input validation
  • Enforce context isolation per session
  • Limit API access to authorised users only

Timeline

  • 2026-08-30: Vulnerability discovered
  • 2026-08-31: Public disclosure
Download Tool