OpenAI GPT-OSS-2-B is a technology platform tracked across 1 threat cluster and 1 intelligence report mention on ThreatCluster. First observed November 7, 2025; most recent activity November 7, 2025.
OpenAI GPT-OSS-2-B is a GPT-based large language model platform highlighted by Cisco for its inclusion among popular LLMs that are susceptible to iterative attack techniques. It exhibits characteristics such as susceptibility to multi-step prompt chaining that can bypass safety mechanisms and potentially expose sensitive data, making it a notable cybersecurity risk. This underscores the importance of robust defenses, monitoring, and adversarial testing in LLM deployments.
Cisco's research reveals that popular open-weight large language models (LLMs) are highly vulnerable to multi-turn prompt injection attacks. These adaptive adversarial attacks can achieve success rates exceeding 90%…