MediumVulnerabilityLLM-specific
CVE-2025-10875: Mulesoft Anypoint Code Builder code injection via LLM prompt input
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2025-10875
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.2%
Summary
CVE-2025-10875 is an Improper Neutralization of Input Used for LLM Prompting vulnerability in Salesforce Mulesoft Anypoint Code Builder that allows Code Injection. The issue affects Mulesoft Anypoint Code Builder before 1.11.6 and is classified as CWE-94, Improper Control of Generation of Code ('Code Injection'). NVD has not yet provided an assessment.
Mitigation
Upgrade to Mulesoft Anypoint Code Builder 1.11.6 or later. The source identifies versions before 1.11.6 as affected and links a Salesforce vendor advisory (help.salesforce.com, article 005228032).
Related items
- InfoTop agent skill security resources — November 2026Similar attack · Adversa AI Blog
- InfoHow to Turn AI Red Team Findings Into Runtime ControlsSimilar attack · Straiker Blog
- MediumDocker Sandboxes vulnerability lets AI agents access sensitive files outside their sandbox (CVE-2026-103916) | Endor LabsSimilar attack · Endor Labs Blog
- MediumFree the Model, Sell the Gateway: Prompt Adware hidden in Jailbreak BundlesSimilar attack · Check Point Research
- InfoRight Tool, Wrong Parameters: Defending LLM Agents Against Parameter PoisoningSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)