ConciseSignal

Salesforce AI vulnerabilities allowed silent CRM data theft

Security firm Zenity Labs found zero-click vulnerabilities in Salesforce Agentforce that let attackers steal sensitive CRM data without user interaction or credentials. Attackers could embed malicious instructions in public forms, which AI agents processed later, leading to unauthorized data exfiltration. The issues, reported in June, were fixed by Salesforce in August. Researchers warn this risk pattern could affect other AI agents handling untrusted input.

Why it mattersThis exposure highlights a new type of risk in automated AI agents processing external data, which could affect a broad range of business systems beyond Salesforce if unaddressed.

Sources covering this

The RegisterHeadline onlySalesforce Agentforce vulns allowed 0-click CRM data theft, anonymous phishing7:01 PM →Dark ReadingHeadline only'Salesbleed' Exploits Salesforce Agents to Enable Slack Phishing9:04 PM →SecurityWeekHeadline only‘SalesBleed’ Flaws in Salesforce Agentforce Enabled Zero-Click Data Exfiltration9:27 AM →Infosecurity MagazineZero-Click Vulnerabilities in Salesforce Agentforce Expose Wider AI Agent Risk1:30 PM →

How it unfolded

  • The Register Salesforce Agentforce vulns allowed 0-click CRM data theft, anonymous phishing
  • Dark Reading 'Salesbleed' Exploits Salesforce Agents to Enable Slack Phishing
  • SecurityWeek ‘SalesBleed’ Flaws in Salesforce Agentforce Enabled Zero-Click Data Exfiltration
  • Infosecurity Magazine Zero-Click Vulnerabilities in Salesforce Agentforce Expose Wider AI Agent Risk

In this story

Salesforce
Concise Signal DailyEverything that mattered, every weekday at 7am.

More in Cybersecurity

11 sources · 7d ago

Security startup Hacktron exploits vulnerability in OpenAI forum

Hacktron, an AI cybersecurity startup, found and exploited a security flaw in OpenAI's community forum that allowed access to an employee's internal account using Anthropic's Claude. The breach relied on an image processing vulnerability and was executed in less than 72 hours. Hacktron stopped short of accessing internal code and reported the issue to OpenAI, which then revoked affected tokens. Hacktron received a $6,500 bounty for the discovery.

14 sources · 3d ago

Hackers claim FBI breach and theft of agent data

A hacking group known as ShinyHunters claims to have breached FBI systems and accessed personal data on thousands of FBI agents and job applicants, including names, home addresses, and phone numbers. Both TechCrunch and 404 Media reviewed samples provided by the hackers and confirmed that some details matched public records. The FBI jobs site and special agent applicant portal were down as of publication. The FBI declined to comment.

9 sources · 3d ago

Microsoft dismantles AI-driven EvilTokens cybercrime platform

Microsoft and partners have taken down EvilTokens, an AI-powered cybercrime platform allegedly used by about 1,000 cybercriminals to compromise over 12,000 Microsoft user email inboxes worldwide. On September 15, Microsoft seized 50 EvilTokens-operated websites and disabled more than 175 related domains. Authorities have arrested two suspects in London accused of fraud and money laundering linked to the platform. At least $1.7 million in losses are tied to EvilTokens.

14 sources · 17d ago

Microsoft releases record number of security patches

Microsoft released updates to fix at least 974 security vulnerabilities across Windows and other products, its largest patch release to date. The update includes critical flaws, some already being exploited, and over 100 rated as dangers that could let attackers seize control of systems. The unprecedented volume is partly due to the use of AI for vulnerability detection, but experts warn that rapid growth complicates efforts to test and deploy fixes.