Security flaws in Salesforce Agentforce allowed poisoned leads to hijack its AI agents, silently steal CRM data without requiring a click, and send phishing messages under the agents’ identities. Zenity Labs uncovered the three vulnerabilities, collectively called SalesBleed, and reported them to Salesforce, which worked with the AI agent security provider to fix the issues.
Salesforce Agentforce vulns allowed 0-click CRM data theft, anonymous phishing
About this summary. This is a short, independently written summary of an article first published by The Register. Cyber Security News did not report or verify the underlying story. Read the original: https://www.theregister.com/security/2026/09/24/salesforce-agentforce-vulns-allowed-0-click-crm-data-theft-anonymous-phishing/5298958
Source attribution: headline and facts are from The Register (theregister.com). Summary method: excerpt of the source description. See our source attribution policy.
Related coverage
Email Prompt Injection: The New Phishing Risk Hiding in Enterprise Inboxes
A seemingly harmless email can contain instructions meant for the AI assistant that handles, summarizes, or acts on your email. This is important as organizations start…
'Salesbleed' Exploits Salesforce Agents to Enable Slack Phishing
Agentic AI can smuggle arbitrary instructions from the Web, across multiple apps, into trusted internal communications channels.
Trust and the enticing consultancy offer
Welcome to this week’s edition of the Threat Source newsletter. In the cybersecurity industry, trust is the invisible currency. Every practitioner carries the implicit…
Someone went shopping in ASUS's eShop – for customer data
Asus has warned eShop customers that an intruder got into part of its online store and may have helped themselves to contact details and order records. The PC maker…
One URL, Three Different Tricks, (Thu, Sep 24th)
Yesterday, we received a phishing email with an interesting link. At first sight, it looks like garbage, but every piece of it has been carefully crafted to confuse…
CLOSEDQUORUM, the malware that asks four AI models what to do next
Cisco Talos finds CLOSEDQUORUM, malware that lets four commercial AI models vote on its next move, with no human operator required. Cisco Talos found malware, dubbed…