CVE-2026-126767 Details
Description
OpsTree REMS through 1.0.0 contains a prompt injection vulnerability that allows authenticated users to disclose the hidden system prompt by submitting crafted chat input to POST /api/v1/rca/chat. Attackers can instruct the assistant to ignore its rules and reveal internal orchestration instructions, aiding the crafting of further prompt injection attacks.
A prompt injection vulnerability has been identified in OpsTree REMS versions through 1.0.0. This vulnerability allows authenticated users to disclose hidden system prompts by submitting crafted chat input to the RCA Chat API. Exploitation of this vulnerability enables attackers to instruct the AI assistant to ignore its rules and reveal internal orchestration instructions, which could be used to craft further prompt injection attacks.
This vulnerability has been patched by OpsTree Solutions. The recommended controls include enforcing a strict separation between user input and internal prompts, preventing the disclosure of system instructions to users, and implementing detection and response mechanisms for prompt injection attacks.
Metrics
CVSS 4.0 Severity and Vector Strings:
CVSS 3.x Severity and Vector Strings:
No data available for CVSS Version 2.0 on this CVE.
Volerion
Assessed Nov 11, 2026CISA-ADP
Assessed Nov 12, 2026References to Advisories, Solutions, and Tools
By selecting these links, you will be leaving this site. These are references gathered from the official CVE record and are not endorsed by Volerion.
Weakness Enumeration
No weakness enumeration is available for this CVE.
Affected Products
| Product | Versions |
|---|---|
| OpsTree REMS | <= 1.0.0 (semver) |
CPE
Remediation
| |
Change History
2 change records found show changes
| Date | Action | Recorded By |
|---|---|---|
| Nov 12, 2026 | CVE Modified | CISA-ADP |
| Nov 11, 2026 | New CVE Received | [email protected] |
Volerion