ForcedLeak flaw in Salesforce Agentforce allows data exfiltration via indirect prompt injection; Salesforce issues patch.
New report outlines the Top 25 MCP vulnerabilities and how attackers could exploit AI agents, plus strategies for defense.
Applications are prime targets for attackers, and breaches often start with a single vulnerability. Application penetration ...
Salesforce Agentforce allowed attackers to hide malicious instructions in routine customer forms, tricking the AI into ...
The Register on MSN
Prompt injection – and a $5 domain – trick Salesforce Agentforce into leaking sales
More fun with AI agents and their security holes A now-fixed flaw in Salesforce’s Agentforce could have allowed external ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback