CVE-2026-75857
Exec tool auto‑approves interactive shells, letting untrusted LLM input run commands.
- CVSS 7.3
- CWE-269
- Authentication, Authorization, and Session Management
- Remote
CodeWhale versions >= 0.8.41 and < 0.8.64 contain a vulnerability in the exec_shell_interact (alias exec_interact) tool, whose approval_requirement returns ApprovalRequirement::Auto. This overrides the default Required approval for code-executing tools, so LLM-controlled stdin is written into an already-approved long-running interactive shell (e.g., a python3 -i REPL, mysql, ssh, or sudo -i session) without any approval prompt. An attacker who can inject instructions via untrusted content the agent ingests (a fetched page, MCP result, or repo file) can cause commands to run at the privilege level of that approved process. Fixed in 0.8.64.
- CWE
- CWE-269
- CVSS base score
- 7.3
- Published
- 2026-08-18
- OWASP
- A03 Injection
- Orthogonal defect classification
- Checking
- Code defect classification
- Missing Check
- Category
- Authentication, Authorization, and Session Management
- Subcategory
- Privilege Escalation
- Accessibility scope
- Remote
- Impact
- Arbitrary Code Execution
- Affected component
- CodeWhale
Solution
Upgrade CodeWhale to version 0.8.64 or later.
Vulnerable code sample
import enum
class ApprovalRequirement(enum.Enum):
Auto = "auto"
Required = "required"
class ExecShellInteract:
def __init__(self, command):
self.command = command
# VULNERABLE: returns Auto, bypassing required approval
def approval_requirement(self):
return ApprovalRequirement.Auto
def run(self):
req = self.approval_requirement()
if req == ApprovalRequirement.Required:
raise PermissionError("Approval needed")
# Simulated execution of an interactive shell
return f"Executing: {self.command}"Patched code sample
import enum
class ApprovalRequirement(enum.Enum):
Auto = "auto"
Required = "required"
class ExecShellInteract:
def __init__(self, command):
self.command = command
# FIX: enforce required approval
def approval_requirement(self):
return ApprovalRequirement.Required
def run(self):
req = self.approval_requirement()
if req == ApprovalRequirement.Required:
raise PermissionError("Approval needed")
# Simulated execution of an interactive shell
return f"Executing: {self.command}"Cite this entry
@misc{vaitp:cve202675857,
title = {{Exec tool auto‑approves interactive shells, letting untrusted LLM input run commands.}},
author = {Bogaerts, Fr\'ed\'eric and Ivaki, Naghmeh and Fonseca, Jos\'e},
year = {2026},
note = {VAITP Python Vulnerability Dataset, entry CVE-2026-75857},
howpublished = {\url{https://netpack.pt/vaitp/vulnerability/CVE-2026-75857/}}
}
Introducing the "VAITP dataset": a specialized repository of Python vulnerabilities and patches, meticulously compiled for the use of the security research community. As Python's prominence grows, understanding and addressing potential security vulnerabilities become crucial. Crafted by and for the cybersecurity community, this dataset offers a valuable resource for researchers, analysts, and developers to analyze and mitigate the security risks associated with Python. Through the comprehensive exploration of vulnerabilities and corresponding patches, the VAITP dataset fosters a safer and more resilient Python ecosystem, encouraging collaborative advancements in programming security.
The supreme art of war is to subdue the enemy without fighting.
Sun Tzu – “The Art of War”
:: Shaping the future through research and ingenuity ::
