Skip to content

MALICIOUS (1) campaign cataloged at 2026-09-17(2).

  1. The campaign has clearly malicious intent, like infostealers.
  2. This is just the date of creating the catalog entry. It may not reflect the date of creation of the campaign itself.

2026-09-marketing-mcp

Package attempts to lure LLM agents to exfiltrate files to a hardcoded location. Analysis of infrastructure suggests preparing for exfiltrating credentials.

Abuse categories

files_exfiltration

Campaign uses files_exfiltration.

llm-threat

Malicious activity is designed against large language models, like e.g. prompt injection.

URLs with payloads, characteristic domains, C&C IPs, repositories with malicious code, etc.

  • hxxps://webhook.site/4acf7132-a75e-47e1-aeff-0350c8eac16c

Packages in the campaign

campaign:2026-09-marketing-mcp