{"data":{"id":"d122d421-8494-408f-ba29-031f81b1bdaa","title":"Meet GPT-Red: an LLM super-hacker OpenAI built to make its models safer","summary":"OpenAI built GPT-Red, an AI model trained to attack other AI systems, and uses it to find security weaknesses before releasing new versions like GPT-5.6. GPT-Red specializes in finding prompt injection attacks (where hackers hide malicious instructions in text that the AI reads), including a previously unknown attack type called fake chain of thought where false information is inserted into the AI's internal reasoning process. The model trains against other AI systems in a self-play loop (where it repeatedly attacks while others defend) within simulated real-world scenarios, making it better at finding effective attacks than human testers alone.","solution":"N/A -- no mitigation discussed in source.","labels":["safety","research"],"sourceUrl":"https://www.technologyreview.com/2026/07/15/1140514/meet-gpt-red-an-llm-super-hacker-openai-built-to-make-its-models-safer/","publishedAt":"2026-07-15T17:09:37.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection"],"issueType":"news","affectedPackages":null,"affectedVendors":["OpenAI"],"affectedVendorsRaw":["OpenAI","GPT-Red","GPT-5.6"],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"patchAvailable":null,"disclosureDate":"2026-07-15T17:09:37.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["safety","integrity"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.85,"researchCategory":null,"atlasIds":null}}