A researcher has disclosed the details of the AI attack method he has named ‘Comment and Control’.
The post Claude Code, Gemini CLI, GitHub Copilot Agents Vulnerable to Prompt Injection via Comments appeared first on SecurityWeek.
‘ZombieAgent’ Attack Let Researchers Take Over ChatGPT
Radware bypassed ChatGPT’s protections to exfiltrate user data and implant a persistent logic into the agent’s long-term memory.
The post ‘ZombieAgent’ Attack Let Researchers Take Over ChatGPT appeared first on SecurityWeek.
Google Patches Gemini AI Hacks Involving Poisoned Logs, Search Results
Researchers found more methods for tricking an AI assistant into aiding sensitive data theft.
The post Google Patches Gemini AI Hacks Involving Poisoned Logs, Search Results appeared first on SecurityWeek.
Salesforce AI Hack Enabled CRM Data Theft
Prompt injection has been leveraged alongside an expired domain to steal Salesforce data in an attack named ForcedLeak.
The post Salesforce AI Hack Enabled CRM Data Theft appeared first on SecurityWeek.
