MediumNewsLLM-specific

'Salesbleed' Exploits Salesforce Agents to Enable Slack Phishing

Source: Dark Reading(opens in a new tab)
Published: September 24, 2026
Record updated: October 9, 2026

Summary

Researchers describe an attack named 'Salesbleed' that abuses Salesforce agents. According to the source, agentic AI can carry arbitrary instructions from the Web, across multiple apps, into trusted internal communications channels. The source text provides no further detail on the mechanics, affected versions or impact.

Details

Scores and exploitation

Disclosure date: September 24, 2026

Weaknesses and techniques

AI threat technique (MITRE ATLAS): AML.T0051

Affected

Vendors: Microsoft

Classification

Attack type: Prompt injection
Attack sophistication: Moderate
AI component targeted: Agent
Impact: Confidentiality,
Integrity
Labels: security,
industry

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative.

Original source: https://www.darkreading.com/application-security/salesbleed-exploits-salesforce-agents-slack-phishing

First tracked: September 24, 2026 at 08:00 PM ET, from Dark Reading

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 85% (self-assessed)

Corrections

2026-10-10: Severity changed from high to medium. Severity capped at medium. High and critical measure technical exploitability and are reserved for vulnerabilities and incidents; this record is a news report.

All corrections

Summary

Related items