Skip to main content

Mistral Vibe

7 CVEs product

Monthly

CVE-2026-87988 Sep 11, 14:35 CRITICAL Act Now

Arbitrary file access in Mistral Vibe, Mistral AI's agentic coding assistant, lets an attacker read (and potentially modify) files outside the intended workspace by abusing commands the agent treats as unconditionally allowed. Because these allowlisted commands skip path validation, the agent executes them against arbitrary filesystem paths without prompting for user approval, breaking the workspace sandbox boundary. Reported by HiddenLayer; no public exploit identified at time of analysis, and no EPSS/KEV data provided.

Mistral Vibe
NVD
CVSS 4.0
10.0
EPSS
0.3%
CVE-2026-87987 Sep 11, 14:34 CRITICAL Act Now

Arbitrary code execution in Mistral Vibe (mistralai:mistral-vibe) lets an attacker defeat the agent's command-approval allowlist by prefixing an allowlisted command with shell environment-variable assignments (e.g. FOO=bar allowedcmd). The permission checker inspects only the command token and skips the leading assignments, so attacker-controlled variables such as LD_PRELOAD or PATH execute arbitrary code without user approval. Reported by HiddenLayer; no public exploit identified at time of analysis and not listed in CISA KEV.

RCE Mistral Vibe
NVD
CVSS 4.0
10.0
EPSS
0.3%
CVE-2026-87986 Sep 11, 14:31 CRITICAL Act Now

Arbitrary code execution in Mistral AI's Mistral Vibe agentic coding assistant lets attackers smuggle commands past the built-in command-approval gate by wrapping them in shell constructs the tool's parser cannot interpret; the unparsed fragments are silently dropped from the permission inspection and then handed to the shell, so embedded commands run on the user's machine without the expected approval prompt. All versions covered by the mistralai:mistral-vibe CPE are affected. Publicly documented in a HiddenLayer security advisory; no public exploit identified at time of analysis and the CVE is not in CISA KEV.

RCE Mistral Vibe
NVD
CVSS 4.0
10.0
EPSS
0.4%
CVE-2026-87985 Sep 11, 14:26 CRITICAL Act Now

Arbitrary code execution in Mistral Vibe lets attackers slip past the tool's command-approval allowlist by wrapping malicious arguments in ANSI-C quoting ($'...'), which the permission checker fails to inspect. Any user running the affected AI coding agent can be tricked into executing attacker-controlled shell code without the usual approval prompt. Reported by HiddenLayer with no public exploit identified at time of analysis, though the advisory documents the bypass technique in detail.

RCE Mistral Vibe
NVD
CVSS 4.0
10.0
EPSS
0.4%
CVE-2026-87984 Sep 11, 14:24 CRITICAL Act Now

Arbitrary file write in Mistral Vibe (the AI coding agent), introduced in version 1.3.4, lets an attacker create or overwrite files anywhere the Vibe process can reach - without triggering the tool's user-approval gate. The root cause is that shell redirection targets (e.g. '>' and '>>') are stripped from permission evaluation, so an otherwise allowlisted command can silently redirect its output to paths outside the active workspace. Reported by HiddenLayer; publicly detailed in their security advisory, with no public exploit code identified at time of analysis and no CISA KEV listing.

Path Traversal Mistral Vibe
NVD
CVSS 4.0
9.3
EPSS
0.4%
CVE-2026-87983 Sep 11, 14:22 CRITICAL Act Now

Arbitrary file read in Mistral Vibe (Mistral AI's agentic coding assistant), introduced in version 2.6.0, lets attackers read files outside the active workspace sandbox without triggering user approval. The flaw stems from improper handling of quotation marks during path validation: a quoted absolute path embedded in an allowlisted shell command is treated as permitted, bypassing the workspace restriction that normally confines the agent. No public exploit identified at time of analysis and no EPSS/KEV signal is available, but the HiddenLayer advisory documents the bypass technique.

Path Traversal Mistral Vibe
NVD
CVSS 4.0
9.2
EPSS
0.4%
CVE-2026-67623 Aug 05, 13:27 HIGH PATCH This Week

Remote code execution in Mistral Vibe before 2.23.3 allows any attacker who can deliver a crafted repository to a victim to execute arbitrary commands with the victim's full OS privileges. The mechanism is git's core.fsmonitor hook: Mistral Vibe calls git status --porcelain without suppressing hook execution, so a malicious fsmonitor entry embedded in a repository's .git/config is executed whenever any vibe command runs inside that repository. No public exploit or CISA KEV listing has been identified at time of analysis; however, the attack pattern is straightforward and the fix is confirmed at v2.23.3.

RCE Mistral Vibe
NVD GitHub
CVSS 4.0
8.6
EPSS
0.5%
EPSS 0% CVSS 10.0
CRITICAL Act Now

Arbitrary file access in Mistral Vibe, Mistral AI's agentic coding assistant, lets an attacker read (and potentially modify) files outside the intended workspace by abusing commands the agent treats as unconditionally allowed. Because these allowlisted commands skip path validation, the agent executes them against arbitrary filesystem paths without prompting for user approval, breaking the workspace sandbox boundary. Reported by HiddenLayer; no public exploit identified at time of analysis, and no EPSS/KEV data provided.

Mistral Vibe
NVD
EPSS 0% CVSS 10.0
CRITICAL Act Now

Arbitrary code execution in Mistral Vibe (mistralai:mistral-vibe) lets an attacker defeat the agent's command-approval allowlist by prefixing an allowlisted command with shell environment-variable assignments (e.g. FOO=bar allowedcmd). The permission checker inspects only the command token and skips the leading assignments, so attacker-controlled variables such as LD_PRELOAD or PATH execute arbitrary code without user approval. Reported by HiddenLayer; no public exploit identified at time of analysis and not listed in CISA KEV.

RCE Mistral Vibe
NVD
EPSS 0% CVSS 10.0
CRITICAL Act Now

Arbitrary code execution in Mistral AI's Mistral Vibe agentic coding assistant lets attackers smuggle commands past the built-in command-approval gate by wrapping them in shell constructs the tool's parser cannot interpret; the unparsed fragments are silently dropped from the permission inspection and then handed to the shell, so embedded commands run on the user's machine without the expected approval prompt. All versions covered by the mistralai:mistral-vibe CPE are affected. Publicly documented in a HiddenLayer security advisory; no public exploit identified at time of analysis and the CVE is not in CISA KEV.

RCE Mistral Vibe
NVD
EPSS 0% CVSS 10.0
CRITICAL Act Now

Arbitrary code execution in Mistral Vibe lets attackers slip past the tool's command-approval allowlist by wrapping malicious arguments in ANSI-C quoting ($'...'), which the permission checker fails to inspect. Any user running the affected AI coding agent can be tricked into executing attacker-controlled shell code without the usual approval prompt. Reported by HiddenLayer with no public exploit identified at time of analysis, though the advisory documents the bypass technique in detail.

RCE Mistral Vibe
NVD
EPSS 0% CVSS 9.3
CRITICAL Act Now

Arbitrary file write in Mistral Vibe (the AI coding agent), introduced in version 1.3.4, lets an attacker create or overwrite files anywhere the Vibe process can reach - without triggering the tool's user-approval gate. The root cause is that shell redirection targets (e.g. '>' and '>>') are stripped from permission evaluation, so an otherwise allowlisted command can silently redirect its output to paths outside the active workspace. Reported by HiddenLayer; publicly detailed in their security advisory, with no public exploit code identified at time of analysis and no CISA KEV listing.

Path Traversal Mistral Vibe
NVD
EPSS 0% CVSS 9.2
CRITICAL Act Now

Arbitrary file read in Mistral Vibe (Mistral AI's agentic coding assistant), introduced in version 2.6.0, lets attackers read files outside the active workspace sandbox without triggering user approval. The flaw stems from improper handling of quotation marks during path validation: a quoted absolute path embedded in an allowlisted shell command is treated as permitted, bypassing the workspace restriction that normally confines the agent. No public exploit identified at time of analysis and no EPSS/KEV signal is available, but the HiddenLayer advisory documents the bypass technique.

Path Traversal Mistral Vibe
NVD
EPSS 1% CVSS 8.6
HIGH PATCH This Week

Remote code execution in Mistral Vibe before 2.23.3 allows any attacker who can deliver a crafted repository to a victim to execute arbitrary commands with the victim's full OS privileges. The mechanism is git's core.fsmonitor hook: Mistral Vibe calls git status --porcelain without suppressing hook execution, so a malicious fsmonitor entry embedded in a repository's .git/config is executed whenever any vibe command runs inside that repository. No public exploit or CISA KEV listing has been identified at time of analysis; however, the attack pattern is straightforward and the fix is confirmed at v2.23.3.

RCE Mistral Vibe
NVD GitHub

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy