OpenHuman desktop agent shell tool sandbox bypass leads to arbitrary command execution

MITRE NVD CVE.ORG JSON API Print: PDF PDF

Summary

CVECVE-2026-55743
StatePUBLISHED
AssignerTuranSec
Source PriorityCVE Program / NVD first with legacy fallback
Published2026-06-17 15:17:02 UTC
Updated2026-06-17 17:17:27 UTC
DescriptionThe shell tool command allowlist in the SecurityPolicy of OpenHuman desktop agent through 0.54.0 (default Supervised security policy) can be bypassed to execute arbitrary OS commands with the privileges of the desktop user. Two flaws in src/openhuman/security/policy.rs combine: (1) is_args_safe() blocks the find flags -exec and -ok but not the functionally identical -execdir and -okdir, which also execute an arbitrary command for each matched file; and (2) skip_env_assignments() strips leading inline KEY=value environment-variable assignments before allowlist validation, so a command such as GIT_EXTERNAL_DIFF=<cmd> git diff is validated as the allowed git diff but, when executed via the shell, runs <cmd> through git's environment-driven hooks (for example GIT_EXTERNAL_DIFF or GIT_SSH_COMMAND). Because the sandbox is the primary trust boundary between untrusted LLM-processed content and the host operating system, an attacker can achieve remote code execution via indirect prompt injection: a malicious document, email, calendar event, or web page ingested by the agent instructs it to run a benign-looking allowlisted command, resulting in arbitrary command execution, data exfiltration, arbitrary file read/write, and lateral movement on the user's machine. The issue was fixed in commit 60050aa09a870f53ed7e4cd40ed41fd2860329e7 (first released in 0.54.22-staging; first stable release 0.56.0), which blocks -execdir/-okdir for find.

Risk And Classification

Primary CVSS: v4.0 9.4 CRITICAL from 309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c

CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Problem Types: CWE-78 | CWE-184 | CWE-78 CWE-78 Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') | CWE-184 CWE-184 Incomplete List of Disallowed Inputs

VersionSourceTypeScoreSeverityVector
4.0309f9ea4-e3e9-4c6c-b79d-e8eb01244f2cSecondary9.4CRITICALCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/C...
4.0CNACVSS9.4CRITICALCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H
3.1309f9ea4-e3e9-4c6c-b79d-e8eb01244f2cSecondary9.6CRITICALCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
3.1CNACVSS9.6CRITICALCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H

CVSS v4.0 Breakdown

Attack Vector
Network
Attack Complexity
Low
Attack Requirements
None
Privileges Required
None
User Interaction
Passive
Confidentiality
High
Integrity
High
Availability
High
Sub Conf.
High
Sub Integrity
High
Sub Availability
High

CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

CVSS v3.1 Breakdown

Attack Vector
Network
Attack Complexity
Low
Privileges Required
None
User Interaction
Required
Scope
Changed
Confidentiality
High
Integrity
High
Availability
High

CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H

Vendor Declared Affected Products

SourceVendorProductVersionPlatforms
CNA Tinyhumansai OpenHuman affected 0.54.0 semver macOS, Windows, Linux

References

ReferenceSourceLinkTags
github.com/tinyhumansai/openhuman 309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c github.com
github.com/tinyhumansai/openhuman/blob/v0.53.49-staging/src/openhuman/se... 309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c github.com
github.com/tinyhumansai/openhuman/commit/60050aa09a870f53ed7e4cd40ed41fd... 309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c github.com
CVE Program record CVE.ORG www.cve.org canonical
NVD vulnerability detail NVD nvd.nist.gov canonical, analysis

Vendor Comments And Credit

Discovery Credit

CNA: Bobur Abdugafforov (en)

CNA: Zikrillayev Salohiddin (en)

© CVE.report 2026 |

Use of this information constitutes acceptance for use in an AS IS condition. There are NO warranties, implied or otherwise, with regard to this information or its use. Any use of this information is at the user's risk. It is the responsibility of user to evaluate the accuracy, completeness or usefulness of any information, opinion, advice or other content. EACH USER WILL BE SOLELY RESPONSIBLE FOR ANY consequences of his or her direct or indirect use of this web site. ALL WARRANTIES OF ANY KIND ARE EXPRESSLY DISCLAIMED. This site will NOT BE LIABLE FOR ANY DIRECT, INDIRECT or any other kind of loss.

CVE, CWE, and OVAL are registred trademarks of The MITRE Corporation and the authoritative source of CVE content is MITRE's CVE web site. This site includes MITRE data granted under the following license.

Free CVE JSON API cve.report/api

CVE.report and Source URL Uptime Status status.cve.report