Security Digest · Vulnerability record
CVE-2026-0755: gemini-mcp-tool vulnerable to OS command injection and @file exfiltration via prompt quoting (CVE-2026-0755)
gemini-mcp-tool execAsync Command Injection Remote Code Execution Vulnerability.
CVSS 9.8 Critical EPSS 3.4% · p89
Should you act?
Critical and remotely reachable
No known exploitation yet, but it is network-reachable without credentials. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.
- No confirmed exploitation. It is not in CISA’s KEV catalog and CISA’s SSVC assessment records no known exploitation. That can change quickly after a public write-up; re-check if you are affected.
- EPSS 3.4%, percentile 89: FIRST’s model estimates a 3.4% chance of exploitation activity in the next 30 days, higher than 89% of all scored CVEs (elevated). EPSS is a probability, not a verdict.
- Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
- Only applies if your dependency tree includes
gemini-mcp-tool(npm) >= 1.1.2, < 1.1.6, fixed in 1.1.6. Check your lockfile, including transitive dependencies.
What it is
gemini-mcp-tool execAsync Command Injection Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of gemini-mcp-tool. Authentication is not required to exploit this vulnerability. The specific flaw exists within the implementation of the execAsync method. The issue results from the lack of proper validation of a user-supplied string before using it to execute a system call. An attacker can leverage this vulnerability to execute code in the context of the service account. Was ZDI-CAN-27783.
From the GitHub advisory
Untrusted prompt input could reach the Gemini CLI @file parser, allowing read/exfiltration of arbitrary local files (@/etc/passwd, @~/.ssh/idrsa, @../../secret). On Windows, unquoted cmd.exe metacharacters could break out into OS command injection.
Fix (1.1.6): removed the broken shell:false double-quote wrapping; added assertSafeFileReferences() to contain @file refs to the working directory; hardened Windows cmd.exe argument quoting.
Weakness type: CWE-78.
Product: gemini-mcp-tool (npm) · Assigned by: zdi · Published: 2026-01-23
Affected and fixed versions
| Ecosystem | Package | Vulnerable | First fixed |
|---|---|---|---|
| npm | gemini-mcp-tool | >= 1.1.2, < 1.1.6 | 1.1.6 |
| Vendor | Product | Affected versions (per CVE record) |
|---|---|---|
| Gemini MCP Tool | gemini-mcp-tool | 1.1.2 |
Severity scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| zdi | 3.0 | 9.8 Critical | CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| GitHub | 3.1 | 9.8 | CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
- Attack vector: network (remotely reachable)
- Attack complexity: low
- Privileges required: none (no login)
- User interaction: none
- Scope: unchanged
CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.
Exploitation and urgency
- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation none, automatable yes, technical impact total.
- FIRST EPSS (model of 2026-10-21): 3.42% probability of exploitation activity in the next 30 days; percentile 89.
Timeline
- — CVE record last updated
- — CVE record published by zdi
- — GitHub-reviewed advisory GHSA-4h5r-5jm8-jxjm published (critical)
Sources and references
Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.
Vulnerability records
- GitHub Advisory GHSA-4h5r-5jm8-jxjm github.com
- CVE.org record CVE-2026-0755 cve.org
- NVD entry CVE-2026-0755 nvd.nist.gov
Other references from the CVE record and advisory
- ZDI-26-021 zerodayinitiative.com
- github.com github.com