Atlassian’s AI assistant Rovo can be manipulated by hidden prompt injection instructions into sending the logged-in user’s Jira and Confluence data to attackers, with the…
Atlassian’s AI assistant Rovo can be manipulated by hidden prompt injection instructions into sending the logged-in user’s Jira and Confluence data to attackers, with the…
TrojPix enables data exfiltration from air-gapped systems through subtle pixel manipulation, but requires malware to already be installed on the target machine.
Poisoned MCP tool descriptions can trick AI agents into exfiltrating business-critical data to external systems while each individual step appears legitimate.
Lockdown Mode restricts ChatGPT functions to prevent data exfiltration through prompt injection attacks and is being rolled out gradually to all user types.
