MediumVulnerabilityLLM-specific
CVE-2025-64320: Salesforce Agentforce Vibes Extension code injection via LLM prompt input
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2025-64320
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.2%
Summary
CVE-2025-64320 is an Improper Neutralization of Input Used for LLM Prompting vulnerability in the Salesforce Agentforce Vibes Extension. It allows Code Injection, classified as CWE-94, and affects versions before 3.2.0. NVD has not yet provided an assessment.
Mitigation
Fixed in 3.2.0 or later, the version boundary implied by the affected range "before 3.2.0".
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)