Atlassian Rovo Vulnerability Allows Exfiltration of Jira and Confluence Data via Prompt Injection

Atlassian Rovo has a vulnerability allowing attackers to exfiltrate Jira and Confluence data through prompt injection or URL parameter manipulation. One exploit was fixed server-side, while another remains unresolved as of August 2026.

Attacker-controlled instructions can make Atlassian's Rovo assistant collect Jira or Confluence data that a signed-in user can access, then send it to an outside server. Two security firms found that behavior independently, by different routes. Only one of those routes is confirmed closed.

PromptArmor, an AI security firm, hid the instructions in content Rovo reads. It said an uploaded file was

Read original article