Atlassian Rovo AI Vulnerable to Prompt Injection, Leaking Jira Data

TechNadu · x · 2026-08-14

Security firm PromptArmor revealed that Atlassian's Rovo AI can be exploited via indirect prompt injection to leak sensitive Jira and Confluence data. The demonstration showed attackers exfiltrating ticket data and full documents to an external URL, a threat vector that persists even when web search is disabled.

Related event: Atlassian Rovo AI Prompt Injection Flaw Unpatched for Months(2 posts)→

Original post →

More from Safety

Safety channel →