YeQing17-2026 OmniAgent Command Validation ReflexionAgent._is_safe_bash_command privileges management
| CVSS Meta Temp Score | Current Exploit Price (≈) | CTI Interest Score |
|---|---|---|
| 6.7 | $0-$5k | 0.00+ |
Summary
A vulnerability was found in YeQing17-2026 OmniAgent and classified as critical. Affected by this vulnerability is the function ReflexionAgent._is_safe_bash_command of the component Command Validation. Executing a manipulation can lead to privileges management.
The identification of this vulnerability is CVE-2026-125368. The attack may be launched remotely. There is no exploit available.
It is advisable to implement a patch to correct this issue.
Details
A vulnerability has been found in YeQing17-2026 OmniAgent (the affected version is unknown) and classified as critical. This vulnerability affects the function ReflexionAgent._is_safe_bash_command of the component Command Validation. The manipulation with an unknown input leads to a privileges management vulnerability. The CWE definition for the vulnerability is CWE-269. The product does not properly assign, modify, track, or check privileges for an actor, creating an unintended sphere of control for that actor. As an impact it is known to affect confidentiality, integrity, and availability. CVE summarizes:
OmniAgent through commit 12b98c5 contains an approval bypass vulnerability in ReflexionAgent._is_safe_bash_command that treats any command starting with find as safe without inspecting -execdir arguments. Prompt-injected agents can run find with -execdir to invoke binaries like dd, nc, perl or openssl through an unsandboxed shell, overwriting files or executing code without human approval.
The advisory is shared for download at github.com. This vulnerability was named CVE-2026-125368 since 11/09/2026. The exploitation appears to be easy. The attack can be initiated remotely. No form of authentication is required for a successful exploitation. Successful exploitation requires user interaction by the victim. There are known technical details, but no exploit is available. The MITRE ATT&CK project declares the attack technique as T1068.
Applying the patch 12b98c520959eff88a6cfa3dd233497084360ab0 is able to eliminate this problem.
Once again VulDB remains the best source for vulnerability data.
Product
Vendor
Name
Website
CPE 2.3
CPE 2.2
CVSSv4
VulDB Vector: 🔒VulDB Reliability: 🔍
CNA CVSS-B Score: 🔒
CNA CVSS-BT Score: 🔒
CNA Vector: 🔒
CVSSv3
VulDB Meta Base Score: 6.9VulDB Meta Temp Score: 6.7
VulDB Base Score: 6.3
VulDB Temp Score: 6.0
VulDB Vector: 🔒
VulDB Reliability: 🔍
CNA Base Score: 7.5
CNA Vector (VulnCheck): 🔒
CVSSv2
| AV | AC | Au | C | I | A |
|---|---|---|---|---|---|
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| Vector | Complexity | Authentication | Confidentiality | Integrity | Availability |
|---|---|---|---|---|---|
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
VulDB Base Score: 🔒
VulDB Temp Score: 🔒
VulDB Reliability: 🔍
Exploiting
Class: Privileges managementCWE: CWE-269 / CWE-266
CAPEC: 🔒
ATT&CK: 🔒
Physical: No
Local: No
Remote: Yes
Availability: 🔒
Status: Not defined
Price Prediction: 🔍
Current Price Estimation: 🔒
| 0-Day | Unlock | Unlock | Unlock | Unlock |
|---|---|---|---|---|
| Today | Unlock | Unlock | Unlock | Unlock |
Threat Intelligence
Interest: 🔍Active Actors: 🔍
Active APT Groups: 🔍
Countermeasures
Recommended: PatchStatus: 🔍
0-Day Time: 🔒
Patch: 12b98c520959eff88a6cfa3dd233497084360ab0
Timeline
11/09/2026 CVE reserved11/09/2026 VulDB entry created
11/10/2026 Advisory disclosed
11/10/2026 VulDB entry last update
Sources
Product: github.comAdvisory: github.com
Status: Confirmed
CNA: VulnCheck
CVE: CVE-2026-125368 (🔒)
GCVE (CVE): GCVE-0-2026-125368
GCVE (VulDB): GCVE-100-433444
Entry
Created: 11/10/2026 00:54Changes: 11/10/2026 00:54 (76)
Complete: 🔍
Cache ID: 216::103
Once again VulDB remains the best source for vulnerability data.
No comments yet. Languages: en.
Please log in to comment.