Loading story…
Zenity Labs disclosed three now-patched SalesBleed vulnerabilities in Salesforce Agentforce that allowed attackers to plant indirect prompt injections through public Salesforce Web-to-Lead forms. When an employee later asked Agentforce about a seemingly legitimate lead, hidden instructions in the poisoned record could direct the General CRM subagent to retrieve other CRM records available under its existing permissions, without requiring the employee to click or approve an action.
The researchers demonstrated exfiltration through DNS requests initiated by externally sourced HTML image URLs after bypassing Agentforce's Trusted URLs redaction safeguards; Slack link unfurling also contributed to the data-leak chain. A separate flaw in Slack-thread replies enabled Agentforce to send messages without confirmation or visible attribution, allowing anonymous phishing as the trusted agent. Salesforce remediated the reported issues, with Zenity confirming the final fixes on September 21.
Track how attackers are adapting to this technology.
5 events from the most recent confirmed update back to the earliest known activity.
Zenity tested Salesforce's remediations and confirmed that all three SalesBleed vulnerabilities had been fixed.
Zenity confirmed Salesforce had fixed the Trusted URLs URL-redaction bypass used in the SalesBleed data-exfiltration chain.
Salesforce confirmed that fixes for the reported SalesBleed vulnerabilities were complete. Zenity subsequently validated the Trusted URLs bypass remediation the following day.
Salesforce confirmed to Zenity that it was working on fixes for the reported SalesBleed vulnerabilities.
Zenity Labs reported three Salesforce Agentforce vulnerabilities collectively called SalesBleed to Salesforce. The flaws enabled Web-to-Lead indirect prompt injection, zero-click CRM-data exfiltration, and phishing through Slack-thread replies.
Vulnerabilities, threat actors, malware, products, organizations, breaches, and observables Mallory has linked to this story. Indicator values are masked here and available in full in the app.
Indicator values are masked on this page. See the values in Mallory Domains, IPs, hashes, and URLs are exportable to your SIEM.
Follow how adversaries are adapting to this technology, and where it touches your stack today.
8 references tracked. Mallory keeps watching after this page renders.
securityweek.com
Open sourcecyberaccord.com
Open sourcecybersecuritynews.com
Open sourcecryptika.com
Open sourcetheregister.com
Open sourceyoutube.com
Open sourcelabs.zenity.io
Open sourcedatatracker.ietf.org
Open sourceMap indicators from this story to your assets and identify affected systems in minutes.
Every observed campaign, victim, and pivot linked to actors named in this story.
Malware, exploits, and IOCs connected to the activity described here.
YARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Get matching new stories delivered to your team as they break — not the next morning.
Ask questions about this story and take action on the answers.
Other stories Mallory is tracking that overlap on entities, sources, or topic labels.
A critical vulnerability known as ForcedLeak was discovered in Salesforce Agentforce, an AI-driven CRM automation platform, allowing attackers to exfiltrate sensitive customer data through indirect prompt injection. Researchers at Noma Security identified that the flaw could be exploited via the Web-to-Lead feature, where malicious instructions embedded in form fields tricked the AI agent into leaking confidential CRM information. The attack enabled threat actors to transmit data such as customer contacts, sales pipeline details, and internal communications to attacker-controlled domains by leveraging weaknesses in context validation and content security policies. Salesforce has since patched the vulnerability, which was rated CVSS 9.4, after coordinated disclosure. The incident highlights the expanded attack surface introduced by autonomous AI agents compared to traditional prompt-response systems.
Jun 29, 2026
Researchers disclosed critical weaknesses in **Salesforce Marketing Cloud** (formerly ExactTarget) that could have allowed cross-tenant exposure of subscriber data, sent emails, SMS records, click tracking, and other marketing data. AMPScript and SSJS template-injection paths could query unrestricted Data Views, while legacy encrypted query strings used by email-view, Cloud Pages, and Forward-to-a-Friend features were vulnerable to CBC padding-oracle and obsolete XOR-based cryptographic attacks, enabling parameter decryption and forgery. Salesforce replaced the affected protection with AES-GCM, expired links generated before January 23, 2026, and disabled double evaluation of AMPScript in email subject lines; it said it found no confirmed unauthorized access or misuse tied to the issues. Separate research documented how an exposed Uber testing endpoint for Salesforce ExactTarget previously let authenticated users submit arbitrary AMPScript through a preview function. The flaw permitted queries against Uber’s `driver_partners` data extension, returning driver UUIDs, join dates, email addresses, and first names, and allowed outbound HTTP GET requests through ExactTarget infrastructure. Assetnote reported that issue in November 2017, Uber remediated it within two days, and the report earned a total HackerOne bounty of $23,000.
Sep 3, 2026
Searchlight Cyber disclosed multiple patched vulnerabilities in **Salesforce Marketing Cloud (SFMC)** that could have exposed private email data across hundreds of organizations on Salesforce’s shared infrastructure. The issues affected **AMPScript**, **SSJS**, **CloudPages**, email rendering, and legacy tracking and email-view links, creating paths for template injection, subscriber enumeration, access to internal data views, and forged or decrypted tracking parameters. Researchers said one key flaw came from double evaluation of AMPScript in email subject lines, allowing unsanitized subscriber input to be executed during rendering, while another involved argument injection through the `MicrositeURL` function. Researchers also found weak protections on legacy links, including a static XOR-based scheme and unauthenticated CBC encryption that could act as a padding oracle, enabling decryption and forgery of links and raising the risk of **cross-tenant** access to sent email content, contact lists, SMS records, and click-tracking data. Salesforce said the flaws were reported on **16 January 2026** and mitigated between **21 and 24 January**, including disabling subject-line double evaluation, migrating Marketing Cloud Engagement encryption to **AES-GCM**, rotating keys, and invalidating older tracking, CloudPages, and email-view links created before **21 January 2026 23:00 UTC**; the company said it found no confirmed unauthorized customer data access or malicious exploitation.
Jun 29, 2026