Topic

Prompt Injection

Coverage tagged prompt injection.

Articles: 2
Desks: 2

Data graphic: SalesBleed, a zero-click attack on Salesforce Agentforce, flowing from a public Web-to-Lead form through a poisoned lead record and an Accounts query to a URL on a .fun domain whose DNS lookup leaks CRM data; no authentication needed, no CVE assigned, fixed by Salesforce on August 18, 2026.

SalesBleed: A Public Web Form Let Attackers Pull Agentforce CRM Data Out Over DNS

Zenity's SalesBleed used a public Web-to-Lead form and two URL-redaction bypasses to make Salesforce Agentforce leak CRM data over DNS.

Oct 2 · 3 min

Diagram-style illustration of indirect prompt injection spreading from a poisoned email or document into an enterprise AI agent’s tools.

stableResearch Prompt Injection

Indirect Prompt Injection Puts Enterprise AI Agents at Risk—and Filters Alone Will Not Stop It

Assume injection succeeds, then contain it with architecture, least privilege, isolation and monitoring rather than betting the estate on a single classifier.

Jul 16 · 8 min