Home/AI Incident Database/ForcedLeak: indirect prompt injection exfiltrates CRM data from an enterprise agent
ForcedLeak: indirect prompt injection exfiltrates CRM data from an enterprise agent
Instructions hidden in a web-to-lead form submission were later processed by an Agentforce agent, which followed them to query lead records and send the data to an attacker's domain that had been allowed by an expired entry in a content security policy.
Contribute
Spot an error, or know a record we should add? Members can propose additions and submit corrections.