Topic
3 posts tagged “Prompt Injection”.
Chisato · · 6 min read CoSnitch let one click on a link make Microsoft Copilot exfiltrate a victim's Gmail and Drive data. How the chained flaw worked and why Varonis called it meta-hacking.
Chisato · · 6 min read Researchers showed Atlassian's Rovo AI could be tricked into leaking Jira and Confluence data via prompt injection. Here's how RovoBlast worked.
Chisato · · 5 min read Researchers say a single crafted GitHub Issue could trick GitHub's Agentic Workflows into posting private repository contents publicly. Here's how GitLost works.
