Atlassian Rovo Can Be Tricked Into Sending Jira and Confluence Data to Attackers

Atlassian’s Rovo assistant has two vulnerabilities that could allow attackers to exfiltrate data. The first, a one-click link flaw, has been patched by Atlassian. The second, a content-borne prompt injection attack, allows attackers to trick Rovo into sending data to external servers, though this vulnerability remains unresolved as of August 8, 2026. While the immediate risk is contained due to the fix, organizations need to review Rovo access permissions and connector scopes to mitigate the ongoing content-borne risk.