AdvisoriesToolsStatsChecklistSubmitGet the email
← All tools
Models & APIs · OpenAI

OpenAI

GPT models, ChatGPT and the OpenAI API.

3Advisories
0critical
2high
1medium
2024-11-18Latest
Timeline · advisories per quarter
12024 Q2
12024 Q3
12024 Q4
Named in sources

Reported for OpenAI

01. highPrompt injectionOWASP LLM01:2025: prompt injection is the top LLM app riskOWASP ranks prompt injection first in its Top 10 for LLM Applications 2025. Any app that feeds untrusted text to a model with tools or data access is exposed. OpenAI Anthropic Claude Google Gemini +4 more 2024-11-18 02. highPrompt injectionSpAIware: prompt injection writes into ChatGPT’s long-term memoryEmbrace The Red showed untrusted content planting persistent instructions in ChatGPT’s memory on the macOS app, so later chats kept sending data to the attacker. OpenAI 2024-09-20
Same pattern

Also worth checking

01. mediumJailbreakMany-shot jailbreaking: long context windows weaken refusalsAnthropic published research showing that filling a long prompt with many fake dialogue examples can push models into answering requests they would normally refuse. Anthropic Claude OpenAI Google Gemini +2 more 2024-04-02
The weekly email

One email a week. Only what changed.

New advisories, CVEs and fixes for Lovable, Bolt, v0, Replit, Base44 and Cursor apps. No roundups of things you already read.