Skip to main content
Mallory
← Back to News
ai-platform-securitydata-exfiltration-method

Google Details Gemini Defenses Against Prompt-Injection Data Theft via URLs

Emerging Technology Risk · 2 sources · Updated 1mo ago · First seen Mar 9, 2026

Google Details Gemini Defenses Against Prompt-Injection Data Theft via URLs

Google detailed layered defenses designed to prevent Gemini and other Google agents from leaking sensitive information through attacker-controlled URLs. Prompt injection can manipulate an agent into embedding secrets in a URL, exposing that data when the address is fetched automatically or clicked by a user. Earlier research published by Embrace The Red demonstrated prompt-injection-driven data exfiltration in Google Bard, highlighting the attack class that Google's mitigations address.

Google's URL provenance system checks whether output URLs originated from non-generative sources, while a server-side markdown sanitizer removes most markdown images, validates links, and escapes embedded HTML. URL reputation signals and narrowly scoped, per-agent allowlists provide additional controls while accommodating legitimate URL generation. Google cautions that these measures mitigate URL-based exfiltration rather than eliminate it: low-bandwidth side channels and alternative exfiltration methods remain possible. Enterprises should therefore treat these protections as defense in depth, not a guarantee that agents can safely process untrusted content alongside sensitive information.

New surface, new adversariesTrack how attackers are adapting to this technology.
Track this risk
Event timeline

How this story unfolded

Events from the most recent confirmed update back to the earliest known activity.

2 events
  1. Reported Mar 9, 20269mo ago

    Google develops server-side markdown sanitization for Gemini

    Google developed a markdown sanitizer that removes images except those using data: URLs, validates link destinations against URL provenance, and escapes embedded HTML. Google reports that markdown sanitization and URL provenance have mitigated URL-based data exfiltration attacks in Gemini.

    Mitigating URL-based Exfiltration in Gemini - Google Bug Hunters
  2. Reported Mar 9, 20269mo ago

    Google develops URL provenance checks to mitigate agent-driven data exfiltration

    Google developed a system that tracks URLs from user prompts and other sources, then checks model-generated URLs and tool inputs against that provenance. The checks verify that URLs originated from non-generative sources, helping prevent agents from constructing attacker-controlled URLs containing sensitive data.

    Mitigating URL-based Exfiltration in Gemini - Google Bug Hunters
Linked entities

Related entities

Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.

Open in app →

Organizations

1 linked
Google
Do you run this?Follow how adversaries are adapting to this technology, and where it touches your stack today.
Track This Risk
Mallory platform

See the full picture, correlated to your attack surface.

This page covers what’s public. Mallory adds the parts that aren’t: which of your assets are affected, which threat actors are using it right now, and what to deploy next.

Exposure mappingMap indicators from this story to your assets and identify affected systems in minutes.
Threat actor evidenceEvery observed campaign, victim, and pivot linked to actors named in this story.
Associated malwareMalware, exploits, and IOCs connected to the activity described here.
Detection signaturesYARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Scheduled alertsGet matching new stories delivered to your team as they break, not the next morning.
AI threadsAsk questions about this story and take action on the answers.