Hidden PDF text can hijack Atlassian's Rovo AI assistant
PromptArmor says Atlassian's Rovo can be steered to exfiltrate Jira tickets and Confluence docs via hidden instructions in uploaded PDFs — a zero-click attack with no approval prompt. It works even when web search is disabled, since the URL-opening tool stays live. Atlassian got the report on May 23 but Rovo 'remains vulnerable,' the firm says.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Z.ai CEO Jie Tang: GLM 5.3 gains come from RL, not parameter count
- New tool adds 14 skills to Claude Code and Cursor for Markdown diagrams
- Tool turns Claude into a team of AI employees on your Mac
- GOP panics over Big Tech ties as Trump shifts on AI regulation
- Ethan Mollick: Claude's skill creator beats ChatGPT for reusable skills