AIDecryptabout 2 hours ago
Hidden PDF Text Hijacks Atlassian Rovo AI Agent
1 min read
Atlassian's Rovo AI agent is vulnerable to indirect prompt injection via hidden white-on-white PDF text, letting attackers exfiltrate Jira tickets and Confluence documents without user approval. Security firm PromptArmor reported the flaw to Atlassian on May 23, 2026, but Rovo remained vulnerable as of August 5.
Level
Hype check
Tap to vote and see what everyone thinks.
Summary by ByteBrief
