PandasAI, an open source project by SinaptikAI, has been found vulnerable to Prompt Injection attacks. An attacker with access to the chat prompt can craft malicious input that is interpreted as code, ...
Hackers can hijack ChatGPT, Claude, and Gemini with nothing but a sentence. OpenAI says the problem may never be fully solved.
As South African businesses increasingly deploy AI agents across HR, finance and supply-chain operations, cybersecurity experts are warning that a new threat is emerging: prompt injection attacks that ...