all InfoSec news
Vertex AI Studio data exfiltration
Oct. 19, 2023, midnight |
The Open Cloud Vulnerability & Security Issue Database www.cloudvulndb.org
markdown tags. This could have allowed an adversary whose data makes it into
the chat context (e.g., via an uploaded file) to achieve
exfiltration of the victim’s data by rendering hyperlinks. However, the severity of this issue is low,
as there were no integrations that could pull remote content. This means
Indirect Prompt Injection was not possible, and it would require the victim to copy
the …
adversary attack chat context data data exfiltration exfiltration file injection injection attack issue llm low markdown prompt prompt injection return severity studio tags vertex vertex ai victim
More from www.cloudvulndb.org / The Open Cloud Vulnerability & Security Issue Database
AWS Amplify IAM role publicly assumable exposure
1 month, 2 weeks ago |
www.cloudvulndb.org
AWS Glue database password leakage
1 month, 3 weeks ago |
www.cloudvulndb.org
Synapse Analytics privilege escalation via intelligent caching
2 months, 3 weeks ago |
www.cloudvulndb.org
Azure Site Recovery privilege escalation
3 months, 2 weeks ago |
www.cloudvulndb.org
Azure HDInsight privilege escalation and DoS vulnerabilities
3 months, 3 weeks ago |
www.cloudvulndb.org
Jobs in InfoSec / Cybersecurity
CyberSOC Technical Lead
@ Integrity360 | Sandyford, Dublin, Ireland
Cyber Security Strategy Consultant
@ Capco | New York City
Cyber Security Senior Consultant
@ Capco | Chicago, IL
Sr. Product Manager
@ MixMode | Remote, US
Security Compliance Strategist
@ Grab | Petaling Jaya, Malaysia
Cloud Security Architect, Lead
@ Booz Allen Hamilton | USA, VA, McLean (1500 Tysons McLean Dr)