Artificial Intelligence
The tech giant found that many indirect prompt injection attempts are harmless, but some malicious exploits have also been identified.
Hi, what are you looking for?
SecurityWeek
All posts tagged "prompt injection"
Artificial Intelligence
A researcher has disclosed the details of the AI attack method he has named ‘Comment and Control’.
Artificial Intelligence
Through the new program, OpenAI will reward reports covering design or implementation issues leading to material harm.
Vulnerabilities
Attackers can inject malicious instructions in a GitHub Issue that are automatically processed by Copilot when launching a Codespace from that issue.
Artificial Intelligence
GeminiJack is a zero-click Gemini attack that could have been exploited using specially crafted emails, calendar invites, or documents.
Artificial Intelligence
Chrome’s new agentic browsing protections include user alignment critic, expanded origin-isolation capabilities, and user confirmations.
Artificial Intelligence
Researchers found more methods for tricking an AI assistant into aiding sensitive data theft.
Artificial Intelligence
Prompt injection has been leveraged alongside an expired domain to steal Salesforce data in an attack named ForcedLeak.
Artificial Intelligence
Researchers show how popular AI systems can be tricked into processing malicious instructions by hiding them in images.
Artificial Intelligence
Google Gemini for Workspace can be tricked into displaying a phishing message when asked to summarize an email.
ICS/OT
A PowerShell script included in patch files appears to be triggering false positives by multiple security engines.
Vulnerabilities
Vulnerabilities
Artificial Intelligence
Artificial Intelligence
Vulnerabilities
Oracle has released mitigations for CVE-2026-35273, but it has not said whether it’s a zero-day exploited in ShinyHunters attacks.
Incident Response
Vulnerabilities
