4 threads tagged with “prompt injection”
Microsoft published analysis of critical GenAI threats facing organizations. What's concerning: 66% of orgs are developing custom GenAI apps, 88% worry about indirect prompt injection, 80% cite data l…
Category: Research & Analysis / AI Security
The referenced page is blocked by Cloudflare protection and could not be accessed for full details. The headline suggests research into a prompt-injection vector via a browser address bar for ChatGPT …
Category: Industry News / Research & Tools / Research & Tools
Researchers demonstrated indirect prompt injection in Microsoft 365 Copilot via booby‑trapped documents. Copilot fetched recent emails, hex‑encoded them, and built a clickable Mermaid diagram that exf…
Category: Threat Alerts / Vulnerabilities & Exploits / Vulnerabilities & Exploits
Tenable disclosed a prompt-injection issue affecting Windsurf where malicious filenames can steer model-agent tools (e.g., read_url_content) into executing unintended actions unless user approval is e…
Category: Industry News / Research & Tools / AI Security