Atlassian Rovo Can Be Tricked Into Sending Jira and Confluence Data to Attackers
Summary: Two security firms independently found that attacker-controlled instructions can make Atlassian's Rovo assistant collect Jira and Confluence data a signed-in user can access and send it to an outside server. Varonis showed the rovoChatPrompt URL parameter preloaded instructions into Rovo Chat so one click ran them with the user's privileges, which Atlassian fixed server-side on July 8, 2026, while PromptArmor reported on August 5, 2026 that a file-borne injection still worked with Rovo's web-search option disabled.
What you should know: Rovo is on by default for everyone on Standard, Premium and Enterprise plans, and the content-borne path has no patch - the only lever is scoping which apps and groups can use Rovo at all, with the caveat that blocking one Jira app leaves Rovo Search, Chat and Create available while any other Jira app on the site still has it enabled.
Read the original at The Hacker News ↗
- Topics
- AI Security
- Related
- SECURITY AFFAIRS AI-CYBERSECURITY NEWSLETTER ROUND 8 Cyber Risks · Nov 15, 2026Pentagon Renames CDAO ‘Super Intelligence Office’ Cyber Risks · Nov 15, 2026186 Fake AI Domains Redirect Users to Click Fix Lures, Browser Malware, and Search Hijackers Cyber Risks · Nov 12, 2026