CVE-2026-55743

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

Published Jun 17, 2026 CVSS 4.0 · 9.4 Critical EPSS < 1% KEV · Not listed
Description
The 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.

Remediation

No solution or workaround provided in the CVE record

Tracking

Sign in to view the affected projects.

Advisories

No advisories available
History
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'none', 'Technical Impact': 'total'}, 'version': '2.0.3'}

Type Values Removed Values Added
Description The 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. The 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.
Title OpenHuman Desktop Agent - Shell Tool Sandbox Bypass Leads to Arbitrary Command Execution OpenHuman desktop agent shell tool sandbox bypass leads to arbitrary command execution
Type Values Removed Values Added
Title OpenHuman desktop agent shell tool sandbox bypass leads to arbitrary command execution OpenHuman Desktop Agent - Shell Tool Sandbox Bypass Leads to Arbitrary Command Execution
Type Values Removed Values Added
First Time appeared Tinyhumansai
Tinyhumansai openhuman
Vendors & Products Tinyhumansai
Tinyhumansai openhuman
Type Values Removed Values Added
Description The 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.
Title OpenHuman desktop agent shell tool sandbox bypass leads to arbitrary command execution
Weaknesses CWE-184
CWE-78
References
Metrics cvssV3_1

{'score': 9.6, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H'}

cvssV4_0

{'score': 9.4, 'vector': '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'}

Weaknesses

Sources

Status
PUBLISHED
Assigner
TuranSec
Published
Updated
Aug 10, 2026, 11:44 AM
Reserved
Jun 17, 2026, 12:59 PM
Status
Deferred
Published
Jun 17, 2026, 3:17 PM
Modified
Oct 26, 2026, 11:10 AM