← Back to search

CVE-2026-109429

8.8 HIGHpublic exploit available

Published 2026-10-13 · Updated 2026-10-16

AI risk analysis

Summary
This vulnerability allows attackers to bypass command permission gates by hiding command substitutions within single-quoted variable values, which static parsing tools like tree-sitter-bash fail to detect. The flaw leverages bash's promptvars feature with the ${var@P} operator to execute hidden commands at runtime, enabling silent arbitrary command execution with agent privileges.
Exploitability
Exploitation is moderately difficult requiring attackers to craft specific input that embeds command substitutions within single-quoted variables and then re-expands them using bash's promptvars feature, but requires no user interaction beyond submitting the crafted input.
Blast radius
The impact could be significant as attackers could execute arbitrary commands with the privileges of the agent's terminal session, potentially leading to full system compromise or lateral movement within the affected environment.
Detection
No reliable host or network indicator is derivable from the published description.
Prioritized remediation
Upgrade to Mistral Vibe 2.25.4 or later to address this command permission gate bypass vulnerability.
rcecommand-injectionbashpermission-bypass

Analysis generated locally by garnet-coder (no data left the box). AI-assisted — verify against primary sources before acting.

NVD description

Mistral Vibe before 2.25.4 contains a command permission gate bypass vulnerability that allows attackers to execute arbitrary commands by hiding a command substitution inside a single-quoted variable value that tree-sitter-bash static parsing cannot detect. Attackers can craft input such as embedding a command substitution within a single-quoted variable and re-expanding it with the ${var@P} prompt-transform operator so bash's promptvars feature executes the hidden command at runtime while only the trailing allowlisted command is classified, resulting in silent arbitrary command execution with the privileges of the agent's terminal session.

CVSS vector

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

Weaknesses

CWE-436

Public exploit & PoC references

All references

Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.

Related CVEs

Related by shared AI tags and CWE weakness class. Browse the full archive.